Software Engineer, AI accelerator Runtime
OpenAI · San Francisco, CA · 1 mo ago
HybridEngineering$266k–$445k/yrFull-time
We need to output HTML fragment with sections for headings that have real content. The posting includes: About The Team, About The Role, In This Role, You Might Thrive..., To comply with U.S. export control..., About OpenAI, then a lot of EEO boilerplate, then Compensation Range.
We need to remove boilerplate: cookie/navigation/legal/EEO/equal-opportunity/scam-warning, duplicated lines, application instructions. Also remove "To comply with U.S. export control laws..." maybe that's legal but it's a requirement; but it's not boilerplate? It's a specific requirement; we can keep it as part of role? It's a legal requirement; but it's not a section heading. We can embed in a paragraph.
We need headings: About the team, About the role, Responsibilities (maybe "In This Role, You Will" corresponds to responsibilities), Requirements/Qualifications/Skills (maybe "You Might Thrive In This Role If You Have" corresponds to qualifications/skills), Benefits, Pay, Schedule. Only include sections if posting has real specific content.
We have About The Team content. About The Role content. In This Role, You Will ... that's responsibilities. You Might Thrive ... that's qualifications/skills. Compensation Range: $266K - $445K gives Pay. No explicit Benefits or Schedule. So we should not create Benefits or Schedule sections.
We need to use for section headings. Use
for section headings. Use - for any list of duties/requirements/benefits. The responsibilities are a list of bullet-like sentences but not explicitly bulleted. We could turn them into
- items. Similarly qualifications could be list.
We must preserve all substantive information, not invent or summarize away detail. So we need to include all points from those sections.
Let's extract:
About The Team:
"OpenAI’s Hardware organization develops AI-native silicon and system-level solutions for the unique demands of advanced AI workloads. Building on efforts like Jalapeño, the team is developing future generations of AI-native silicon and tightly integrated systems to power the next generation of frontier models. By co-designing chips, systems, tools, and methodologies, the team helps deliver faster, more efficient, and production-ready hardware for OpenAI’s supercomputing platform."
About The Role:
"You will build the low-level device runtime that turns compiled programs into efficient, functional and performant execution on OpenAI’s custom AI accelerator. This software will schedule kernel launches, manage device memory and address spaces, coordinate synchronization, and expose reliable abstractions to higher-level runtimes and frameworks. You will work at the boundary of software and hardware, partnering with compiler, kernel, architecture, verification, and silicon teams to define interfaces and validate behavior. You will also use and improve event-based, cycle-accurate simulation to develop runtime capabilities before silicon is available, diagnose performance and correctness issues, and guide hardware-software co-design."
In This Role, You Will (Responsibilities):
List:
- Design and implement the low-level device runtime for OpenAI custom silicon.
- Build kernel-launch scheduling, command submission, queueing, dependency tracking, and completion handling.
- Manage device memory spaces, allocation, virtual-to-physical mappings, data movement, and lifetime across concurrent workloads.
- Implement synchronization primitives, events, barriers, streams, and ordering guarantees that are correct and efficient.
- Define clean interfaces between the runtime, drivers, firmware, compiler-generated code, kernels, and higher-level execution systems.
- Use event-based, cycle-accurate simulators to develop, validate, debug, and performance-tune runtime behavior before and after silicon availability.
- Diagnose concurrency, memory-ordering, deadlock, race, correctness, and performance issues across software and hardware boundaries.
- Build tests, tracing, profiling, observability, and reproducible workloads for runtime correctness and performance.
- Partner with architecture and silicon teams to turn workload and simulator insights into hardware-software interface improvements.
You Might Thrive In This Role If You Have (Qualifications/Skills):
List:
- strong low-level systems programming experience in C, C++, Rust, or comparable environments.
- Have built runtimes, drivers, firmware, operating-system components, accelerator software, or adjacent systems infrastructure.
- Understand concurrency, synchronization, asynchronous execution, queues, events, and memory-ordering semantics.
- Understand memory management, address spaces, DMA, caching, coherency, and hardware-software interfaces.
- Have hands-on experience with event-based, cycle-accurate simulators or closely related architectural and performance models.
- Can reason quantitatively about scheduling, latency, throughput, utilization, contention, and resource tradeoffs.
- Are skilled at debugging failures that span software abstractions, device interfaces, and hardware behavior.
- Work effectively across compiler, kernel, architecture, verification, firmware, and silicon teams.
Also there is a line: "To comply with U.S. export control laws and regulations, candidates for this role may need to meet certain legal status requirements as provided in those laws and regulations." This is a requirement; we could include it under Requirements or maybe as a note. Since it's a specific requirement, we can include it in a
under Qualifications or a separate note. Probably include as a bullet under Qualifications.
About OpenAI: description; we could keep as a paragraph under About OpenAI? The instruction says use headings for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. About OpenAI is not listed as a heading; but we could treat it as "About the company" but not in list. However we might keep it as a paragraph without heading? The instruction: "use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It says e.g., not exclusive. But we should only include sections when posting has real specific content. About OpenAI is substantive; we could include a heading like "About OpenAI". It's not in the examples but seems reasonable. However the instruction says "use for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It implies those are typical headings; we can also use others if appropriate. I'd include About OpenAI as About OpenAI
.
We must not repeat the job title as a heading. The job title is not given explicitly; we can ignore.
We must not put Job ID/requisition numbers as headings.
We must remove boilerplate: EEO statements, equal opportunity, accommodation links, privacy policy, scam warning, etc. Also remove "To notify OpenAI that you believe this job posting is non-compliant..." etc. Also remove "Background checks for applicants..." etc. Also remove "For unincorporated Los Angeles County workers..." etc. Also remove "We are committed to providing reasonable accommodations..." etc. Also remove "OpenAI Global Applicant Privacy Policy". Also remove "At OpenAI, we believe artificial intelligence..." etc? That's part of About OpenAI maybe we keep the mission statement? The About OpenAI paragraph includes mission statement; we can keep that.
We need to preserve all substantive information; the mission statement is substantive. So we keep the About OpenAI paragraph: "OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity."
We should not include the EEO boilerplate after that.
Now compile HTML.
Structure:
About the Team
...
About the Role
...
Responsibilities
- ... each bullet
Qualifications
- ... each bullet including export control compliance
About OpenAI
...
Pay
Compensation Range: $266K - $445K
We should not add Benefits or Schedule.
Check that we didn't miss any substantive info: The "About The Team" and "About The Role" paragraphs we captured. The "In This Role, You Will" we turned into responsibilities list. The "You Might Thrive In This Role If You Have" we turned into qualifications list. Also we need to include the line about export control; we can add as a bullet.
Check for any other substantive info: maybe the line "To comply with U.S. export control laws and regulations, candidates for this role may need to meet certain legal status requirements as provided in those laws and regulations." That's a requirement; we added.
Now ensure we didn't include any boilerplate: The EEO statement after About OpenAI, the accommodation link, privacy policy, etc. We removed.
Now output only HTML fragment.
Let's craft.
Be careful to escape any HTML special characters? Not needed.
We'll produce:
About the Team
OpenAI’s Hardware organization develops AI-native silicon and system-level solutions for the unique demands of advanced AI workloads. Building on efforts like Jalapeño, the team is developing future generations of AI-native silicon and tightly integrated systems to power the next generation of frontier models. By co-designing chips, systems, tools, and methodologies, the team helps deliver faster, more efficient, and production-ready hardware for OpenAI’s supercomputing platform.
About the Role
You will build the low-level device runtime that turns compiled programs into efficient, functional and performant execution on OpenAI’s custom AI accelerator. This software will schedule kernel launches, manage device memory and address spaces, coordinate synchronization, and expose reliable abstractions to higher-level runtimes and frameworks. You will work at the boundary of software and hardware, partnering with compiler, kernel, architecture, verification, and silicon teams to define interfaces and validate behavior. You will also use and improve event-based, cycle-accurate simulation to develop runtime capabilities before silicon is available, diagnose performance and correctness issues, and guide hardware-software co-design.
Responsibilities
- Design and implement the low-level device runtime for OpenAI custom silicon.
- Build kernel-launch scheduling, command submission, queueing, dependency tracking, and completion handling.
- Manage device memory spaces, allocation, virtual-to-physical mappings, data movement, and lifetime across concurrent workloads.
- Implement synchronization primitives, events, barriers, streams, and ordering guarantees that are correct and efficient.
- Define clean interfaces between the runtime, drivers, firmware, compiler-generated code, kernels, and higher-level execution systems.
- Use event-based, cycle-accurate simulators to develop, validate, debug, and performance-tune runtime behavior before and after silicon availability.
- Diagnose concurrency, memory-ordering, deadlock, race, correctness, and performance issues across software and hardware boundaries.
- Build tests, tracing, profiling, observability, and reproducible workloads for runtime correctness and performance.
- Partner with architecture and silicon teams to turn workload and simulator insights into hardware-software interface improvements.
Qualifications
- Strong low-level systems programming experience in C, C++, Rust, or comparable environments.
- Have built runtimes, drivers, firmware, operating-system components, accelerator software, or adjacent systems infrastructure.
- Understand concurrency, synchronization, asynchronous execution, queues, events, and memory-ordering semantics.
- Understand memory management, address spaces, DMA, caching, coherency, and hardware-software interfaces.
- Have hands-on experience with event-based, cycle-accurate simulators or closely related architectural and performance models.
- items. Similarly qualifications could be list.
We must preserve all substantive information, not invent or summarize away detail. So we need to include all points from those sections.
Let's extract:
About The Team:
"OpenAI’s Hardware organization develops AI-native silicon and system-level solutions for the unique demands of advanced AI workloads. Building on efforts like Jalapeño, the team is developing future generations of AI-native silicon and tightly integrated systems to power the next generation of frontier models. By co-designing chips, systems, tools, and methodologies, the team helps deliver faster, more efficient, and production-ready hardware for OpenAI’s supercomputing platform."
About The Role:
"You will build the low-level device runtime that turns compiled programs into efficient, functional and performant execution on OpenAI’s custom AI accelerator. This software will schedule kernel launches, manage device memory and address spaces, coordinate synchronization, and expose reliable abstractions to higher-level runtimes and frameworks. You will work at the boundary of software and hardware, partnering with compiler, kernel, architecture, verification, and silicon teams to define interfaces and validate behavior. You will also use and improve event-based, cycle-accurate simulation to develop runtime capabilities before silicon is available, diagnose performance and correctness issues, and guide hardware-software co-design."
In This Role, You Will (Responsibilities):
List:
- Design and implement the low-level device runtime for OpenAI custom silicon.
- Build kernel-launch scheduling, command submission, queueing, dependency tracking, and completion handling.
- Manage device memory spaces, allocation, virtual-to-physical mappings, data movement, and lifetime across concurrent workloads.
- Implement synchronization primitives, events, barriers, streams, and ordering guarantees that are correct and efficient.
- Define clean interfaces between the runtime, drivers, firmware, compiler-generated code, kernels, and higher-level execution systems.
- Use event-based, cycle-accurate simulators to develop, validate, debug, and performance-tune runtime behavior before and after silicon availability.
- Diagnose concurrency, memory-ordering, deadlock, race, correctness, and performance issues across software and hardware boundaries.
- Build tests, tracing, profiling, observability, and reproducible workloads for runtime correctness and performance.
- Partner with architecture and silicon teams to turn workload and simulator insights into hardware-software interface improvements.
You Might Thrive In This Role If You Have (Qualifications/Skills):
List:
- strong low-level systems programming experience in C, C++, Rust, or comparable environments.
- Have built runtimes, drivers, firmware, operating-system components, accelerator software, or adjacent systems infrastructure.
- Understand concurrency, synchronization, asynchronous execution, queues, events, and memory-ordering semantics.
- Understand memory management, address spaces, DMA, caching, coherency, and hardware-software interfaces.
- Have hands-on experience with event-based, cycle-accurate simulators or closely related architectural and performance models.
- Can reason quantitatively about scheduling, latency, throughput, utilization, contention, and resource tradeoffs.
- Are skilled at debugging failures that span software abstractions, device interfaces, and hardware behavior.
- Work effectively across compiler, kernel, architecture, verification, firmware, and silicon teams.
Also there is a line: "To comply with U.S. export control laws and regulations, candidates for this role may need to meet certain legal status requirements as provided in those laws and regulations." This is a requirement; we could include it under Requirements or maybe as a note. Since it's a specific requirement, we can include it in a
under Qualifications or a separate note. Probably include as a bullet under Qualifications. About OpenAI: description; we could keep as a paragraph under About OpenAI? The instruction says use headings for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. About OpenAI is not listed as a heading; but we could treat it as "About the company" but not in list. However we might keep it as a paragraph without heading? The instruction: "use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It says e.g., not exclusive. But we should only include sections when posting has real specific content. About OpenAI is substantive; we could include a heading like "About OpenAI". It's not in the examples but seems reasonable. However the instruction says "use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." It implies those are typical headings; we can also use others if appropriate. I'd include About OpenAI as
About OpenAI
. We must not repeat the job title as a heading. The job title is not given explicitly; we can ignore. We must not put Job ID/requisition numbers as headings. We must remove boilerplate: EEO statements, equal opportunity, accommodation links, privacy policy, scam warning, etc. Also remove "To notify OpenAI that you believe this job posting is non-compliant..." etc. Also remove "Background checks for applicants..." etc. Also remove "For unincorporated Los Angeles County workers..." etc. Also remove "We are committed to providing reasonable accommodations..." etc. Also remove "OpenAI Global Applicant Privacy Policy". Also remove "At OpenAI, we believe artificial intelligence..." etc? That's part of About OpenAI maybe we keep the mission statement? The About OpenAI paragraph includes mission statement; we can keep that. We need to preserve all substantive information; the mission statement is substantive. So we keep the About OpenAI paragraph: "OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity." We should not include the EEO boilerplate after that. Now compile HTML. Structure:About the Team
...
About the Role
...
Responsibilities
- ... each bullet
Qualifications
- ... each bullet including export control compliance
About OpenAI
...
Pay
Compensation Range: $266K - $445K
We should not add Benefits or Schedule. Check that we didn't miss any substantive info: The "About The Team" and "About The Role" paragraphs we captured. The "In This Role, You Will" we turned into responsibilities list. The "You Might Thrive In This Role If You Have" we turned into qualifications list. Also we need to include the line about export control; we can add as a bullet. Check for any other substantive info: maybe the line "To comply with U.S. export control laws and regulations, candidates for this role may need to meet certain legal status requirements as provided in those laws and regulations." That's a requirement; we added. Now ensure we didn't include any boilerplate: The EEO statement after About OpenAI, the accommodation link, privacy policy, etc. We removed. Now output only HTML fragment. Let's craft. Be careful to escape any HTML special characters? Not needed. We'll produce:About the Team
OpenAI’s Hardware organization develops AI-native silicon and system-level solutions for the unique demands of advanced AI workloads. Building on efforts like Jalapeño, the team is developing future generations of AI-native silicon and tightly integrated systems to power the next generation of frontier models. By co-designing chips, systems, tools, and methodologies, the team helps deliver faster, more efficient, and production-ready hardware for OpenAI’s supercomputing platform.
About the Role
You will build the low-level device runtime that turns compiled programs into efficient, functional and performant execution on OpenAI’s custom AI accelerator. This software will schedule kernel launches, manage device memory and address spaces, coordinate synchronization, and expose reliable abstractions to higher-level runtimes and frameworks. You will work at the boundary of software and hardware, partnering with compiler, kernel, architecture, verification, and silicon teams to define interfaces and validate behavior. You will also use and improve event-based, cycle-accurate simulation to develop runtime capabilities before silicon is available, diagnose performance and correctness issues, and guide hardware-software co-design.
Responsibilities
- Design and implement the low-level device runtime for OpenAI custom silicon.
- Build kernel-launch scheduling, command submission, queueing, dependency tracking, and completion handling.
- Manage device memory spaces, allocation, virtual-to-physical mappings, data movement, and lifetime across concurrent workloads.
- Implement synchronization primitives, events, barriers, streams, and ordering guarantees that are correct and efficient.
- Define clean interfaces between the runtime, drivers, firmware, compiler-generated code, kernels, and higher-level execution systems.
- Use event-based, cycle-accurate simulators to develop, validate, debug, and performance-tune runtime behavior before and after silicon availability.
- Diagnose concurrency, memory-ordering, deadlock, race, correctness, and performance issues across software and hardware boundaries.
- Build tests, tracing, profiling, observability, and reproducible workloads for runtime correctness and performance.
- Partner with architecture and silicon teams to turn workload and simulator insights into hardware-software interface improvements.
Qualifications
- Strong low-level systems programming experience in C, C++, Rust, or comparable environments.
- Have built runtimes, drivers, firmware, operating-system components, accelerator software, or adjacent systems infrastructure.
- Understand concurrency, synchronization, asynchronous execution, queues, events, and memory-ordering semantics.
- Understand memory management, address spaces, DMA, caching, coherency, and hardware-software interfaces.
- Have hands-on experience with event-based, cycle-accurate simulators or closely related architectural and performance models.