Senior Software Engineer, Agentic Infrastructure
for section headings. Use - for any list of duties/requirements/benefits, and
for prose. Do NOT repeat job title as heading. Do NOT put Job ID/requisition numbers as headings. Remove boilerplate, navigation, EEO, etc. Preserve all substantive info. Include a section only when posting has real specific content; never emit heading followed by filler/placeholder text. Prefer few substantive sections over many thin ones.
We need to parse the posting.
Key sections:
- Intro paragraph about Relativity Space (maybe not needed as a heading? Could be part of About The Team? Actually there is "About The Team" heading then description. The intro before that is general company description; could be included as a
before sections? The instruction: "use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It doesn't forbid other headings? It says use for section headings (e.g. About the role, Responsibilities...). Likely we should use those headings only for those categories. But we can also have other headings? The instruction: "use for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It suggests those are examples; we can use other headings if appropriate? Probably we should stick to those categories. However we have "About The Team" and "About The Role" and "About You". Those map to About the team, About the role, About you (maybe Qualifications/Skills). We can map: About The Team -> About the Team
. About The Role -> About the Role
. About You -> About You
(could be Qualifications). Nice To Haves -> maybe part of Requirements or Skills. Benefits -> Benefits
. Pay -> Pay
. Schedule -> Schedule
.
We must not create sections with placeholder text. Ensure we have actual content.
Let's extract content.
About The Team paragraph: "Dark Matter Lab is a research group within Relativity Space focused on advanced aerospace systems, agentic engineering, and technologies outside the conventional roadmap. We build the infrastructure needed to turn new ideas into engineering capabilities people can actually depend on."
That's substantive.
About The Role: multiple paragraphs describing responsibilities. We need to turn into - for list of duties. The text includes bullet-like sentences but not actual list. We can convert each sentence into a list item.
Let's extract duties:
- Own the reliability of our agentic infrastructure: agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where good off-the-shelf solutions don't yet exist
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux/macOS systems, Proxmox VMs and containers, storage, backups, and recovery
- Maintain multi-site networking including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools that make engineers faster
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to open-source projects we rely on
- Help design practical security around local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to understand what they need and turn recurring problems into better infrastructure
Also earlier: "We run a stack of interconnected agentic systems — SybilClaw, yapCAD, Mechatron, Multigraph, local LLM inference, an inter-agent message bus, parametric CAD pipelines, a print farm, and the infrastructure connecting it all. We need an engineer who can own and evolve these systems as they move from prototypes into production engineering infrastructure. This role is for someone who has deployed an agentic harness (OpenClaw, Hermes, SybilClaw, or something comparable) in a real work environment. You understand what it takes to make these systems reliable when engineers depend on them every day. You’ll learn the stack, improve it, and work with forward-deployed engineers to package portions of it for deployment with internal and external customers."
We could incorporate some of that as prose before list, but we can also include as list items. However instruction: Use
- for any list of duties/requirements/benefits, and
for prose. So we can have a short paragraph intro then list.
About You: requirements list.
Extract:
- 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, VMs, or containers in production
- Strong networking fundamentals including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient
- Meaningful experience contributing to or maintaining open-source software
- Strong judgment around reliability, security, performance, and simplicity
Nice To Haves But Not Required list:
- Experience with ITAR-regulated, air-gapped, export-controlled, or similarly constrained environments
- Experience operating local LLM inference with Ollama, MLX, vLLM, llama.cpp, or similar
- Experience with model routing, context management, tool execution, agent state, or multi-agent systems
- Experience building internal developer infrastructure used daily by other engineers
- Experience deploying systems into customer or forward-deployed environments
- A GitHub, Gitea, or other body of work where we can see what you've built
Schedule: "This role requires in-office presence at least three days per week, with flexibility to work remotely when the work allows."
Pay: "Hiring Range $154,000—$230,000 USD"
Benefits: "At Relativity Space, we are committed to transparency and fairness in our compensation practices. Actual compensation will be determined based on experience, qualifications, and other job-related factors. Compensation is only one part of our total rewards package. Relativity Space offers competitive salary and equity, a generous PTO and sick leave policy, parental leave, an annual learning and development stipend, and more! To see some of the benefits & perks we offer, please visit here."
We need to extract benefits list: competitive salary and equity, generous PTO and sick leave policy, parental leave, annual learning and development stipend, and more. Could list as items.
We should not include boilerplate like EEO, equal opportunity, unsolicited resumes, accommodation contact, etc. Remove those.
Also remove "To see some of the benefits & perks we offer, please visit here." That's a link; maybe we can keep as prose but not include link? It's okay to keep as prose but not include URL? The instruction: preserve ALL substantive information; do not invent or summarize away detail. The link is substantive? It's a reference; we could keep as plain text "To see some of the benefits & perks we offer, please visit here." That's okay.
Now structure HTML.
We'll start with maybe a
for the introductory paragraph about Relativity Space (the first paragraph). Then sections.
But we must not repeat job title as heading. No job title given.
We'll output:
At Relativity Space, we’re building rockets to serve today’s needs and tomorrow’s breakthroughs. Our Terran R vehicle will deliver customer payloads to orbit, meeting the growing demand for launch capacity. But that’s just the start. Achieving commercial success with Terran R will unlock new opportunities to advance science, exploration, and innovation, pioneering progress that reaches beyond the known. Joining Relativity means becoming part of something where autonomy, ownership, and impact exist at every level. Here, you're not just executing tasks; you're solving problems that haven’t been solved before, helping develop a rocket, a factory, and a business from the ground up. Whether you’re in propulsion, manufacturing, software, avionics, or a corporate function, you’ll collaborate across teams, shape decisions, and see your work come to life in record time. Relativity is a place where creativity and technical rigor go hand in hand, and your voice will help define the stories we’re writing together. Now is a unique moment in time where it’s early enough to leave your mark on the product, the process, and the culture, but far enough along that Terran R is tangible and picking up momentum. The most meaningful work of your career is waiting. Join us.
Then sections.
About the Team
Dark Matter Lab is a research group within Relativity Space focused on advanced aerospace systems, agentic engineering, and technologies outside the conventional roadmap. We build the infrastructure needed to turn new ideas into engineering capabilities people can actually depend on.
About the Role
We run a stack of interconnected agentic systems — SybilClaw, yapCAD, Mechatron, Multigraph, local LLM inference, an inter-agent message bus, parametric CAD pipelines, a print farm, and the infrastructure connecting it all. We need an engineer who can own and evolve these systems as they move from prototypes into production engineering infrastructure. This role is for someone who has deployed an agentic harness (OpenClaw, Hermes, SybilClaw, or something comparable) in a real work environment. You understand what it takes to make these systems reliable when engineers depend on them every day. You’ll learn the stack, improve it, and work with forward-deployed engineers to package portions of it for deployment with internal and external customers.
- Own the reliability of our agentic infrastructure: agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where good off-the-shelf solutions don't yet exist
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux/macOS systems, Proxmox VMs and containers, storage, backups, and recovery
- Maintain multi-site networking including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools that make engineers faster
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to open-source projects we rely on
- Help design practical security around local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to understand what they need and turn recurring problems into better infrastructure
About You
- 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, VMs, or containers in production
- Strong networking fundamentals including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient
- Meaningful
for prose. Do NOT repeat job title as heading. Do NOT put Job ID/requisition numbers as headings. Remove boilerplate, navigation, EEO, etc. Preserve all substantive info. Include a section only when posting has real specific content; never emit heading followed by filler/placeholder text. Prefer few substantive sections over many thin ones. We need to parse the posting. Key sections: - Intro paragraph about Relativity Space (maybe not needed as a heading? Could be part of About The Team? Actually there is "About The Team" heading then description. The intro before that is general company description; could be included as a
before sections? The instruction: "use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It doesn't forbid other headings? It says use for section headings (e.g. About the role, Responsibilities...). Likely we should use those headings only for those categories. But we can also have other headings? The instruction: "use for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It suggests those are examples; we can use other headings if appropriate? Probably we should stick to those categories. However we have "About The Team" and "About The Role" and "About You". Those map to About the team, About the role, About you (maybe Qualifications/Skills). We can map: About The Team -> About the Team
. About The Role -> About the Role
. About You -> About You
(could be Qualifications). Nice To Haves -> maybe part of Requirements or Skills. Benefits -> Benefits
. Pay -> Pay
. Schedule -> Schedule
.
We must not create sections with placeholder text. Ensure we have actual content.
Let's extract content.
About The Team paragraph: "Dark Matter Lab is a research group within Relativity Space focused on advanced aerospace systems, agentic engineering, and technologies outside the conventional roadmap. We build the infrastructure needed to turn new ideas into engineering capabilities people can actually depend on."
That's substantive.
About The Role: multiple paragraphs describing responsibilities. We need to turn into - for list of duties. The text includes bullet-like sentences but not actual list. We can convert each sentence into a list item.
Let's extract duties:
- Own the reliability of our agentic infrastructure: agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where good off-the-shelf solutions don't yet exist
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux/macOS systems, Proxmox VMs and containers, storage, backups, and recovery
- Maintain multi-site networking including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools that make engineers faster
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to open-source projects we rely on
- Help design practical security around local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to understand what they need and turn recurring problems into better infrastructure
Also earlier: "We run a stack of interconnected agentic systems — SybilClaw, yapCAD, Mechatron, Multigraph, local LLM inference, an inter-agent message bus, parametric CAD pipelines, a print farm, and the infrastructure connecting it all. We need an engineer who can own and evolve these systems as they move from prototypes into production engineering infrastructure. This role is for someone who has deployed an agentic harness (OpenClaw, Hermes, SybilClaw, or something comparable) in a real work environment. You understand what it takes to make these systems reliable when engineers depend on them every day. You’ll learn the stack, improve it, and work with forward-deployed engineers to package portions of it for deployment with internal and external customers."
We could incorporate some of that as prose before list, but we can also include as list items. However instruction: Use
- for any list of duties/requirements/benefits, and
for prose. So we can have a short paragraph intro then list.
About You: requirements list.
Extract:
- 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, VMs, or containers in production
- Strong networking fundamentals including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient
- Meaningful experience contributing to or maintaining open-source software
- Strong judgment around reliability, security, performance, and simplicity
Nice To Haves But Not Required list:
- Experience with ITAR-regulated, air-gapped, export-controlled, or similarly constrained environments
- Experience operating local LLM inference with Ollama, MLX, vLLM, llama.cpp, or similar
- Experience with model routing, context management, tool execution, agent state, or multi-agent systems
- Experience building internal developer infrastructure used daily by other engineers
- Experience deploying systems into customer or forward-deployed environments
- A GitHub, Gitea, or other body of work where we can see what you've built
Schedule: "This role requires in-office presence at least three days per week, with flexibility to work remotely when the work allows."
Pay: "Hiring Range $154,000—$230,000 USD"
Benefits: "At Relativity Space, we are committed to transparency and fairness in our compensation practices. Actual compensation will be determined based on experience, qualifications, and other job-related factors. Compensation is only one part of our total rewards package. Relativity Space offers competitive salary and equity, a generous PTO and sick leave policy, parental leave, an annual learning and development stipend, and more! To see some of the benefits & perks we offer, please visit here."
We need to extract benefits list: competitive salary and equity, generous PTO and sick leave policy, parental leave, annual learning and development stipend, and more. Could list as items.
We should not include boilerplate like EEO, equal opportunity, unsolicited resumes, accommodation contact, etc. Remove those.
Also remove "To see some of the benefits & perks we offer, please visit here." That's a link; maybe we can keep as prose but not include link? It's okay to keep as prose but not include URL? The instruction: preserve ALL substantive information; do not invent or summarize away detail. The link is substantive? It's a reference; we could keep as plain text "To see some of the benefits & perks we offer, please visit here." That's okay.
Now structure HTML.
We'll start with maybe a
for the introductory paragraph about Relativity Space (the first paragraph). Then sections.
But we must not repeat job title as heading. No job title given.
We'll output:
At Relativity Space, we’re building rockets to serve today’s needs and tomorrow’s breakthroughs. Our Terran R vehicle will deliver customer payloads to orbit, meeting the growing demand for launch capacity. But that’s just the start. Achieving commercial success with Terran R will unlock new opportunities to advance science, exploration, and innovation, pioneering progress that reaches beyond the known. Joining Relativity means becoming part of something where autonomy, ownership, and impact exist at every level. Here, you're not just executing tasks; you're solving problems that haven’t been solved before, helping develop a rocket, a factory, and a business from the ground up. Whether you’re in propulsion, manufacturing, software, avionics, or a corporate function, you’ll collaborate across teams, shape decisions, and see your work come to life in record time. Relativity is a place where creativity and technical rigor go hand in hand, and your voice will help define the stories we’re writing together. Now is a unique moment in time where it’s early enough to leave your mark on the product, the process, and the culture, but far enough along that Terran R is tangible and picking up momentum. The most meaningful work of your career is waiting. Join us.
Then sections.
About the Team
Dark Matter Lab is a research group within Relativity Space focused on advanced aerospace systems, agentic engineering, and technologies outside the conventional roadmap. We build the infrastructure needed to turn new ideas into engineering capabilities people can actually depend on.
About the Role
We run a stack of interconnected agentic systems — SybilClaw, yapCAD, Mechatron, Multigraph, local LLM inference, an inter-agent message bus, parametric CAD pipelines, a print farm, and the infrastructure connecting it all. We need an engineer who can own and evolve these systems as they move from prototypes into production engineering infrastructure. This role is for someone who has deployed an agentic harness (OpenClaw, Hermes, SybilClaw, or something comparable) in a real work environment. You understand what it takes to make these systems reliable when engineers depend on them every day. You’ll learn the stack, improve it, and work with forward-deployed engineers to package portions of it for deployment with internal and external customers.
- Own the reliability of our agentic infrastructure: agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where good off-the-shelf solutions don't yet exist
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux/macOS systems, Proxmox VMs and containers, storage, backups, and recovery
- Maintain multi-site networking including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools that make engineers faster
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to open-source projects we rely on
- Help design practical security around local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to understand what they need and turn recurring problems into better infrastructure
About You
- 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, VMs, or containers in production
- Strong networking fundamentals including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient
- Meaningful
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It suggests those are examples; we can use other headings if appropriate? Probably we should stick to those categories. However we have "About The Team" and "About The Role" and "About You". Those map to About the team, About the role, About you (maybe Qualifications/Skills). We can map: About The Team -> About the Team
. About The Role -> About the Role
. About You -> About You
(could be Qualifications). Nice To Haves -> maybe part of Requirements or Skills. Benefits -> Benefits
. Pay -> Pay
. Schedule -> Schedule
.
We must not create sections with placeholder text. Ensure we have actual content.
Let's extract content.
About The Team paragraph: "Dark Matter Lab is a research group within Relativity Space focused on advanced aerospace systems, agentic engineering, and technologies outside the conventional roadmap. We build the infrastructure needed to turn new ideas into engineering capabilities people can actually depend on."
That's substantive.
About The Role: multiple paragraphs describing responsibilities. We need to turn into - for list of duties. The text includes bullet-like sentences but not actual list. We can convert each sentence into a list item.
Let's extract duties:
- Own the reliability of our agentic infrastructure: agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where good off-the-shelf solutions don't yet exist
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux/macOS systems, Proxmox VMs and containers, storage, backups, and recovery
- Maintain multi-site networking including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools that make engineers faster
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to open-source projects we rely on
- Help design practical security around local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to understand what they need and turn recurring problems into better infrastructure
Also earlier: "We run a stack of interconnected agentic systems — SybilClaw, yapCAD, Mechatron, Multigraph, local LLM inference, an inter-agent message bus, parametric CAD pipelines, a print farm, and the infrastructure connecting it all. We need an engineer who can own and evolve these systems as they move from prototypes into production engineering infrastructure. This role is for someone who has deployed an agentic harness (OpenClaw, Hermes, SybilClaw, or something comparable) in a real work environment. You understand what it takes to make these systems reliable when engineers depend on them every day. You’ll learn the stack, improve it, and work with forward-deployed engineers to package portions of it for deployment with internal and external customers."
We could incorporate some of that as prose before list, but we can also include as list items. However instruction: Use
- for any list of duties/requirements/benefits, and
for prose. So we can have a short paragraph intro then list.
About You: requirements list.
Extract:
- 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, VMs, or containers in production
- Strong networking fundamentals including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient
- Meaningful experience contributing to or maintaining open-source software
- Strong judgment around reliability, security, performance, and simplicity
Nice To Haves But Not Required list:
- Experience with ITAR-regulated, air-gapped, export-controlled, or similarly constrained environments
- Experience operating local LLM inference with Ollama, MLX, vLLM, llama.cpp, or similar
- Experience with model routing, context management, tool execution, agent state, or multi-agent systems
- Experience building internal developer infrastructure used daily by other engineers
- Experience deploying systems into customer or forward-deployed environments
- A GitHub, Gitea, or other body of work where we can see what you've built
Schedule: "This role requires in-office presence at least three days per week, with flexibility to work remotely when the work allows."
Pay: "Hiring Range $154,000—$230,000 USD"
Benefits: "At Relativity Space, we are committed to transparency and fairness in our compensation practices. Actual compensation will be determined based on experience, qualifications, and other job-related factors. Compensation is only one part of our total rewards package. Relativity Space offers competitive salary and equity, a generous PTO and sick leave policy, parental leave, an annual learning and development stipend, and more! To see some of the benefits & perks we offer, please visit here."
We need to extract benefits list: competitive salary and equity, generous PTO and sick leave policy, parental leave, annual learning and development stipend, and more. Could list as items.
We should not include boilerplate like EEO, equal opportunity, unsolicited resumes, accommodation contact, etc. Remove those.
Also remove "To see some of the benefits & perks we offer, please visit here." That's a link; maybe we can keep as prose but not include link? It's okay to keep as prose but not include URL? The instruction: preserve ALL substantive information; do not invent or summarize away detail. The link is substantive? It's a reference; we could keep as plain text "To see some of the benefits & perks we offer, please visit here." That's okay.
Now structure HTML.
We'll start with maybe a
for the introductory paragraph about Relativity Space (the first paragraph). Then sections.
But we must not repeat job title as heading. No job title given.
We'll output:
At Relativity Space, we’re building rockets to serve today’s needs and tomorrow’s breakthroughs. Our Terran R vehicle will deliver customer payloads to orbit, meeting the growing demand for launch capacity. But that’s just the start. Achieving commercial success with Terran R will unlock new opportunities to advance science, exploration, and innovation, pioneering progress that reaches beyond the known. Joining Relativity means becoming part of something where autonomy, ownership, and impact exist at every level. Here, you're not just executing tasks; you're solving problems that haven’t been solved before, helping develop a rocket, a factory, and a business from the ground up. Whether you’re in propulsion, manufacturing, software, avionics, or a corporate function, you’ll collaborate across teams, shape decisions, and see your work come to life in record time. Relativity is a place where creativity and technical rigor go hand in hand, and your voice will help define the stories we’re writing together. Now is a unique moment in time where it’s early enough to leave your mark on the product, the process, and the culture, but far enough along that Terran R is tangible and picking up momentum. The most meaningful work of your career is waiting. Join us.
Then sections.
About the Team
Dark Matter Lab is a research group within Relativity Space focused on advanced aerospace systems, agentic engineering, and technologies outside the conventional roadmap. We build the infrastructure needed to turn new ideas into engineering capabilities people can actually depend on.
About the Role
We run a stack of interconnected agentic systems — SybilClaw, yapCAD, Mechatron, Multigraph, local LLM inference, an inter-agent message bus, parametric CAD pipelines, a print farm, and the infrastructure connecting it all. We need an engineer who can own and evolve these systems as they move from prototypes into production engineering infrastructure. This role is for someone who has deployed an agentic harness (OpenClaw, Hermes, SybilClaw, or something comparable) in a real work environment. You understand what it takes to make these systems reliable when engineers depend on them every day. You’ll learn the stack, improve it, and work with forward-deployed engineers to package portions of it for deployment with internal and external customers.
- Own the reliability of our agentic infrastructure: agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where good off-the-shelf solutions don't yet exist
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux/macOS systems, Proxmox VMs and containers, storage, backups, and recovery
- Maintain multi-site networking including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools that make engineers faster
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to open-source projects we rely on
- Help design practical security around local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to understand what they need and turn recurring problems into better infrastructure
About You
- 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, VMs, or containers in production
- Strong networking fundamentals including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient
- Meaningful
- for any list of duties/requirements/benefits, and
for prose. So we can have a short paragraph intro then list. About You: requirements list. Extract: - 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation - Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment - Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking - Experience operating physical infrastructure, VMs, or containers in production - Strong networking fundamentals including routing, VLANs, DNS, and firewalls - Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient - Meaningful experience contributing to or maintaining open-source software - Strong judgment around reliability, security, performance, and simplicity Nice To Haves But Not Required list: - Experience with ITAR-regulated, air-gapped, export-controlled, or similarly constrained environments - Experience operating local LLM inference with Ollama, MLX, vLLM, llama.cpp, or similar - Experience with model routing, context management, tool execution, agent state, or multi-agent systems - Experience building internal developer infrastructure used daily by other engineers - Experience deploying systems into customer or forward-deployed environments - A GitHub, Gitea, or other body of work where we can see what you've built Schedule: "This role requires in-office presence at least three days per week, with flexibility to work remotely when the work allows." Pay: "Hiring Range $154,000—$230,000 USD" Benefits: "At Relativity Space, we are committed to transparency and fairness in our compensation practices. Actual compensation will be determined based on experience, qualifications, and other job-related factors. Compensation is only one part of our total rewards package. Relativity Space offers competitive salary and equity, a generous PTO and sick leave policy, parental leave, an annual learning and development stipend, and more! To see some of the benefits & perks we offer, please visit here." We need to extract benefits list: competitive salary and equity, generous PTO and sick leave policy, parental leave, annual learning and development stipend, and more. Could list as items. We should not include boilerplate like EEO, equal opportunity, unsolicited resumes, accommodation contact, etc. Remove those. Also remove "To see some of the benefits & perks we offer, please visit here." That's a link; maybe we can keep as prose but not include link? It's okay to keep as prose but not include URL? The instruction: preserve ALL substantive information; do not invent or summarize away detail. The link is substantive? It's a reference; we could keep as plain text "To see some of the benefits & perks we offer, please visit here." That's okay. Now structure HTML. We'll start with maybe a
for the introductory paragraph about Relativity Space (the first paragraph). Then sections. But we must not repeat job title as heading. No job title given. We'll output:
At Relativity Space, we’re building rockets to serve today’s needs and tomorrow’s breakthroughs. Our Terran R vehicle will deliver customer payloads to orbit, meeting the growing demand for launch capacity. But that’s just the start. Achieving commercial success with Terran R will unlock new opportunities to advance science, exploration, and innovation, pioneering progress that reaches beyond the known. Joining Relativity means becoming part of something where autonomy, ownership, and impact exist at every level. Here, you're not just executing tasks; you're solving problems that haven’t been solved before, helping develop a rocket, a factory, and a business from the ground up. Whether you’re in propulsion, manufacturing, software, avionics, or a corporate function, you’ll collaborate across teams, shape decisions, and see your work come to life in record time. Relativity is a place where creativity and technical rigor go hand in hand, and your voice will help define the stories we’re writing together. Now is a unique moment in time where it’s early enough to leave your mark on the product, the process, and the culture, but far enough along that Terran R is tangible and picking up momentum. The most meaningful work of your career is waiting. Join us.
Then sections.About the Team
Dark Matter Lab is a research group within Relativity Space focused on advanced aerospace systems, agentic engineering, and technologies outside the conventional roadmap. We build the infrastructure needed to turn new ideas into engineering capabilities people can actually depend on.
About the Role
We run a stack of interconnected agentic systems — SybilClaw, yapCAD, Mechatron, Multigraph, local LLM inference, an inter-agent message bus, parametric CAD pipelines, a print farm, and the infrastructure connecting it all. We need an engineer who can own and evolve these systems as they move from prototypes into production engineering infrastructure. This role is for someone who has deployed an agentic harness (OpenClaw, Hermes, SybilClaw, or something comparable) in a real work environment. You understand what it takes to make these systems reliable when engineers depend on them every day. You’ll learn the stack, improve it, and work with forward-deployed engineers to package portions of it for deployment with internal and external customers.
- Own the reliability of our agentic infrastructure: agents, sessions, model routing, context pipelines, inter-agent communication, and supporting services
- Build and maintain infrastructure where good off-the-shelf solutions don't yet exist
- Deploy and operate local LLM inference across Mac Studio and GPU hardware
- Manage Linux/macOS systems, Proxmox VMs and containers, storage, backups, and recovery
- Maintain multi-site networking including L3 routing, VLANs, DNS, firewalls, and connectivity
- Build CLIs, dashboards, automation, and internal tools that make engineers faster
- Improve observability, debugging, and automated failure recovery
- Contribute upstream to open-source projects we rely on
- Help design practical security around local compute, data handling, and access controls
- Package and deploy portions of the stack into internal and customer environments
- Work directly with engineers to understand what they need and turn recurring problems into better infrastructure
About You
- 5+ years of experience building and operating complex software and compute infrastructure, with hands-on work across hardware, operating systems, networking, and automation
- Experience deploying an agentic harness such as OpenClaw, Hermes, SybilClaw, or a comparable system in a real work environment
- Strong Linux and macOS systems experience, including debugging services, processes, storage, permissions, and networking
- Experience operating physical infrastructure, VMs, or containers in production
- Strong networking fundamentals including routing, VLANs, DNS, and firewalls
- Ability to build software, scripts, CLIs, and integrations when existing tools aren't sufficient
- Meaningful