Senior Agent Harness Engineer
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). Use - for any list of duties/requirements/benefits, and
for prose. Do NOT repeat the job title as a heading. Do NOT put Job ID / requisition numbers as headings — fold minor metadata into a short
or drop it. Preserve ALL substantive information; do NOT invent or summarize away detail. Remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. IMPORTANT: include a section ONLY when the posting has real, specific content for it — never emit a heading followed by filler/placeholder text (e.g. "commensurate with experience", "not specified", "N/A", "varies", "TBD") and never create Pay/Schedule/Benefits sections unless the posting actually states them. Prefer a few substantive sections over many thin ones.
We need to decide which sections to include. The posting has:
- About Savvy Wealth (intro paragraph)
- Recognition (list of awards)
- THE ROLE (description)
- What You'll Do (list of responsibilities)
- What We're Looking For (list of qualifications)
- NICE TO HAVE (list)
- Benefits (list)
- Compensation Range (salary)
We should not include sections like "About the role" maybe we can combine "THE ROLE" and "What You'll Do"? But we need headings for sections: maybe "About the role", "Responsibilities", "Requirements", "Benefits", "Pay". The instruction says use those as examples but we can use other headings if appropriate? It says use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we should stick to those headings where applicable. We can map:
- About the role: description of role (THE ROLE + maybe What You'll Do? Actually "What You'll Do" is responsibilities). So we could have About the role (overview) and Responsibilities (list). Or combine.
- Requirements: qualifications (What We're Looking For). Could also include NICE TO HAVE as optional but maybe not separate section; could be part of Requirements? But we could have a separate "Qualifications" for required and "Skills" for nice-to-have? The instruction says we can use Qualifications, Skills. So we could have:
About the role
(overview)
Responsibilities
(list from What You'll Do)
Requirements
(list from What We're Looking For)
Skills
(list from NICE TO HAVE)
Benefits
(list)
Pay
(compensation range)
We must not create sections with filler. All have content.
We must not repeat the job title as a heading. The job title is "first dedicated agentic harness engineer". We won't use that as heading.
We must not include Job ID etc.
We need to preserve all substantive information. So we need to include the intro about Savvy Wealth, recognition, etc. Where to put them? Possibly in About the role section? But About the role should be about the role, not company. However we could include a brief company overview in About the role? The instruction says we can use About the role heading for section headings. It didn't forbid including company info there. But we might want a separate section for company overview? Not in the list of allowed headings. Could we use a
without heading? Yes, we can have prose
without heading. So we can start with a
containing the company overview and recognition. Then headings for sections.
Thus output:
About Savvy Wealth ... recognition ...
Then About the role
with description from THE ROLE (maybe short paragraph). Then Responsibilities
with - list from What You'll Do. Then
Requirements
with - list from What We're Looking For. Then
Skills
with - list from NICE TO HAVE. Then
Benefits
with - list from Benefits. Then
Pay
with Compensation Range: $180K - $235K
.
We must ensure we don't include any boilerplate like "Come build the next stage with us!" maybe that's part of intro; we can keep it.
We need to preserve all substantive information: The intro includes many details: Savvy Wealth description, founder, stats, etc. Also Recognition list. We'll include them in the opening . Might be long but okay.
We must not include application instructions (none present). No duplicated lines.
Let's extract the content.
Intro paragraph:
"About Savvy Wealth Wealth management is a $545 billion industry that still runs on manual work. 75% of advisors offer no digital communication beyond email, and most still build financial plans by hand in Excel. Savvy is reinventing what it looks like to be a financial advisor. Founder Ritik Malhotra saw the fragmentation firsthand after seeking out his own advisor, and started Savvy to give independent advisors a modern, AI-native home. Savvy is a registered investment advisor (RIA), and we partner with experienced financial advisors who want to grow without running the back office themselves. Advisors bring their book and join Savvy, running under their own brand (or ours), and Savvy earns a percentage of the assets they manage. In return, they get a true business-in-a-box: a proprietary tech platform and client portal, an in-house marketing team that helps them grow, a world-class investment management team, and a dedicated client services team that runs day-to-day operations and support. Advisors at Savvy service up to 50% more households and save 19 hours a week. AI runs through everything we do. On the product side, Savvy Intelligence (released April 2026) is the only AI built for wealth managers that can see a client's complete financial picture. Internally, everyone at Savvy uses Claude and is encouraged to experiment with it, backed by a dedicated AI enablement team and a RevOps org building agents in-house. The trajectory is steep and it's still early. We're a Series C company with 170+ people, $200M raised, and $100M ARR in sight this year. Inc. ranked us the No. 1 fastest-growing financial services company in America in 2026. Come build the next stage with us!"
Recognition:
"Recognition We're a Certified Great Place to Work and have been honored for our culture and our growth: Newsweek's America's Greatest Startup Workplaces (2026)Fortune Best Workplaces in New York™ (2026)Great Place to Work Certified™"
We can combine into a paragraph.
Now THE ROLE:
"The ROLE Savvy is hiring our first dedicated agentic harness engineer. Coding agents are already part of how our engineers work, but adoption has moved faster than our ability to make their output consistently good. Wrong code and weak architectural decisions still create review burden. We are hiring someone to treat that as an engineering problem, not solve it with a longer prompt. You will own how developers across EPD interact with coding agents and with the systems around them. That includes the codebase itself, our internal skills and instructions, cloud coding workflows, agentic code review, CI, local development, testing, debugging, and delivery. You will have substantial autonomy to make cross-cutting decisions, change defaults, and set standards across the organization. This is a hands-on platform engineering role. Most of your time will be spent building software and improving the environment in which developers and agents work. You will also talk directly with engineers, study where time and quality are being lost, test your ideas against real work, and help teams adopt better ways of operating. You will join our infrastructure and harness team and partner closely with infrastructure, security, data, and product engineers."
We can put that as About the role paragraph.
Now What You'll Do (list):
- Own developer and agent experience: Set the roadmap for how our engineers and coding agents navigate the codebase, use internal tools, run tests, review changes, and ship software.
- Build the cloud coding experience: Build the developer-facing layer around our existing compute foundations, including task intake, environment setup, context, tools, permissions, observability, review, and delivery.
- Improve agent output at the source: Change repository structure, interfaces, documentation, instructions, and feedback loops so agents produce correct code and sound architecture more consistently.
- Engineer context deliberately: Design what agents receive up front, discover progressively, persist, compact, hand off, or discard. Choose models and reasoning effort based on evidence from the job, not habit.
- Own our internal skills system: Raise the quality of our shared skills and instructions through clear contribution standards, evaluation, discoverability, progressive disclosure, maintenance, and pruning.
- Fix everyday developer friction: Improve CI speed and reliability, local setup, testing, debugging, deploy workflows, and the other bottlenecks that cost engineers time.
- Measure what works: Combine developer research and satisfaction data with DORA or SPACE measures and task-level agent evaluations. Inspect traces, establish baselines, and test whether changes improve correctness, reviewability, cost, latency, and human intervention.
- Drive adoption: Work directly with engineers, teach effective practices, and turn successful experiments into defaults. When the root problem is the codebase or engineering process, make that case and help fix it.
- Partner on safe autonomy: Work with our infrastructure and security engineers on sandboxing, credentials, approvals, auditability, and the controls needed to give cloud agents useful access without giving them unlimited access.
Now What We're Looking For (list):
- Exceptional with coding agents: You use Claude Code, Codex, Cursor, or similar tools for substantial work and can show how you decompose tasks, manage context, choose models, inspect failures, and consistently produce maintainable software. Faster output alone is not the bar.
- Internal tools with real users: You have built developer tooling or a platform that engineers beyond your immediate team relied on. You learned from their behavior and support burden, not only from what they said they wanted.
- CI or large-codebase experience: You have made a meaningful improvement to CI, testing, repository workflows, or developer productivity in a substantial, long-lived codebase.
- Product judgment for internal systems: You can interview developers, separate symptoms from root causes, turn evidence into a roadmap, and say no to attractive work that will not improve the system.
- Strong software engineering: You have built and operated substantial production software. We are open on language and framework, but you must be able to move from diagnosis to a durable implementation yourself.
- Evaluation over intuition: You know that agent behavior is nondeterministic and changing quickly. You compare prompts, context, tools, models, and workflows against representative tasks rather than declaring success from a demo.
- Cross-team influence: You can set standards and change defaults across teams without becoming a gatekeeper. You explain the evidence, earn trust, and remain accountable for the experience you create.
- Pragmatic range: You are comfortable moving between platform code, repository conventions, evaluation data, developer interviews, documentation, and hands-on enablement. This is not a prompt-writing, DevRel, or framework-only role.
Now NICE
for prose. Do NOT repeat the job title as a heading. Do NOT put Job ID / requisition numbers as headings — fold minor metadata into a short
or drop it. Preserve ALL substantive information; do NOT invent or summarize away detail. Remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. IMPORTANT: include a section ONLY when the posting has real, specific content for it — never emit a heading followed by filler/placeholder text (e.g. "commensurate with experience", "not specified", "N/A", "varies", "TBD") and never create Pay/Schedule/Benefits sections unless the posting actually states them. Prefer a few substantive sections over many thin ones. We need to decide which sections to include. The posting has: - About Savvy Wealth (intro paragraph) - Recognition (list of awards) - THE ROLE (description) - What You'll Do (list of responsibilities) - What We're Looking For (list of qualifications) - NICE TO HAVE (list) - Benefits (list) - Compensation Range (salary) We should not include sections like "About the role" maybe we can combine "THE ROLE" and "What You'll Do"? But we need headings for sections: maybe "About the role", "Responsibilities", "Requirements", "Benefits", "Pay". The instruction says use those as examples but we can use other headings if appropriate? It says use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we should stick to those headings where applicable. We can map:
- About the role: description of role (THE ROLE + maybe What You'll Do? Actually "What You'll Do" is responsibilities). So we could have About the role (overview) and Responsibilities (list). Or combine.
- Requirements: qualifications (What We're Looking For). Could also include NICE TO HAVE as optional but maybe not separate section; could be part of Requirements? But we could have a separate "Qualifications" for required and "Skills" for nice-to-have? The instruction says we can use Qualifications, Skills. So we could have:
About the role
(overview)
Responsibilities
(list from What You'll Do)
Requirements
(list from What We're Looking For)
Skills
(list from NICE TO HAVE)
Benefits
(list)
Pay
(compensation range)
We must not create sections with filler. All have content.
We must not repeat the job title as a heading. The job title is "first dedicated agentic harness engineer". We won't use that as heading.
We must not include Job ID etc.
We need to preserve all substantive information. So we need to include the intro about Savvy Wealth, recognition, etc. Where to put them? Possibly in About the role section? But About the role should be about the role, not company. However we could include a brief company overview in About the role? The instruction says we can use About the role heading for section headings. It didn't forbid including company info there. But we might want a separate section for company overview? Not in the list of allowed headings. Could we use a
without heading? Yes, we can have prose
without heading. So we can start with a
containing the company overview and recognition. Then headings for sections. Thus output:
About Savvy Wealth ... recognition ...
ThenAbout the role
with description from THE ROLE (maybe short paragraph). ThenResponsibilities
with- list from What You'll Do. Then
Requirements
with- list from What We're Looking For. Then
Skills
with- list from NICE TO HAVE. Then
Benefits
with- list from Benefits. Then
Pay
withCompensation Range: $180K - $235K
. We must ensure we don't include any boilerplate like "Come build the next stage with us!" maybe that's part of intro; we can keep it. We need to preserve all substantive information: The intro includes many details: Savvy Wealth description, founder, stats, etc. Also Recognition list. We'll include them in the opening. Might be long but okay. We must not include application instructions (none present). No duplicated lines. Let's extract the content. Intro paragraph: "About Savvy Wealth Wealth management is a $545 billion industry that still runs on manual work. 75% of advisors offer no digital communication beyond email, and most still build financial plans by hand in Excel. Savvy is reinventing what it looks like to be a financial advisor. Founder Ritik Malhotra saw the fragmentation firsthand after seeking out his own advisor, and started Savvy to give independent advisors a modern, AI-native home. Savvy is a registered investment advisor (RIA), and we partner with experienced financial advisors who want to grow without running the back office themselves. Advisors bring their book and join Savvy, running under their own brand (or ours), and Savvy earns a percentage of the assets they manage. In return, they get a true business-in-a-box: a proprietary tech platform and client portal, an in-house marketing team that helps them grow, a world-class investment management team, and a dedicated client services team that runs day-to-day operations and support. Advisors at Savvy service up to 50% more households and save 19 hours a week. AI runs through everything we do. On the product side, Savvy Intelligence (released April 2026) is the only AI built for wealth managers that can see a client's complete financial picture. Internally, everyone at Savvy uses Claude and is encouraged to experiment with it, backed by a dedicated AI enablement team and a RevOps org building agents in-house. The trajectory is steep and it's still early. We're a Series C company with 170+ people, $200M raised, and $100M ARR in sight this year. Inc. ranked us the No. 1 fastest-growing financial services company in America in 2026. Come build the next stage with us!" Recognition: "Recognition We're a Certified Great Place to Work and have been honored for our culture and our growth: Newsweek's America's Greatest Startup Workplaces (2026)Fortune Best Workplaces in New York™ (2026)Great Place to Work Certified™" We can combine into a paragraph. Now THE ROLE: "The ROLE Savvy is hiring our first dedicated agentic harness engineer. Coding agents are already part of how our engineers work, but adoption has moved faster than our ability to make their output consistently good. Wrong code and weak architectural decisions still create review burden. We are hiring someone to treat that as an engineering problem, not solve it with a longer prompt. You will own how developers across EPD interact with coding agents and with the systems around them. That includes the codebase itself, our internal skills and instructions, cloud coding workflows, agentic code review, CI, local development, testing, debugging, and delivery. You will have substantial autonomy to make cross-cutting decisions, change defaults, and set standards across the organization. This is a hands-on platform engineering role. Most of your time will be spent building software and improving the environment in which developers and agents work. You will also talk directly with engineers, study where time and quality are being lost, test your ideas against real work, and help teams adopt better ways of operating. You will join our infrastructure and harness team and partner closely with infrastructure, security, data, and product engineers." We can put that as About the role paragraph. Now What You'll Do (list): - Own developer and agent experience: Set the roadmap for how our engineers and coding agents navigate the codebase, use internal tools, run tests, review changes, and ship software. - Build the cloud coding experience: Build the developer-facing layer around our existing compute foundations, including task intake, environment setup, context, tools, permissions, observability, review, and delivery. - Improve agent output at the source: Change repository structure, interfaces, documentation, instructions, and feedback loops so agents produce correct code and sound architecture more consistently. - Engineer context deliberately: Design what agents receive up front, discover progressively, persist, compact, hand off, or discard. Choose models and reasoning effort based on evidence from the job, not habit. - Own our internal skills system: Raise the quality of our shared skills and instructions through clear contribution standards, evaluation, discoverability, progressive disclosure, maintenance, and pruning. - Fix everyday developer friction: Improve CI speed and reliability, local setup, testing, debugging, deploy workflows, and the other bottlenecks that cost engineers time. - Measure what works: Combine developer research and satisfaction data with DORA or SPACE measures and task-level agent evaluations. Inspect traces, establish baselines, and test whether changes improve correctness, reviewability, cost, latency, and human intervention. - Drive adoption: Work directly with engineers, teach effective practices, and turn successful experiments into defaults. When the root problem is the codebase or engineering process, make that case and help fix it. - Partner on safe autonomy: Work with our infrastructure and security engineers on sandboxing, credentials, approvals, auditability, and the controls needed to give cloud agents useful access without giving them unlimited access. Now What We're Looking For (list): - Exceptional with coding agents: You use Claude Code, Codex, Cursor, or similar tools for substantial work and can show how you decompose tasks, manage context, choose models, inspect failures, and consistently produce maintainable software. Faster output alone is not the bar. - Internal tools with real users: You have built developer tooling or a platform that engineers beyond your immediate team relied on. You learned from their behavior and support burden, not only from what they said they wanted. - CI or large-codebase experience: You have made a meaningful improvement to CI, testing, repository workflows, or developer productivity in a substantial, long-lived codebase. - Product judgment for internal systems: You can interview developers, separate symptoms from root causes, turn evidence into a roadmap, and say no to attractive work that will not improve the system. - Strong software engineering: You have built and operated substantial production software. We are open on language and framework, but you must be able to move from diagnosis to a durable implementation yourself. - Evaluation over intuition: You know that agent behavior is nondeterministic and changing quickly. You compare prompts, context, tools, models, and workflows against representative tasks rather than declaring success from a demo. - Cross-team influence: You can set standards and change defaults across teams without becoming a gatekeeper. You explain the evidence, earn trust, and remain accountable for the experience you create. - Pragmatic range: You are comfortable moving between platform code, repository conventions, evaluation data, developer interviews, documentation, and hands-on enablement. This is not a prompt-writing, DevRel, or framework-only role. Now NICE
- list from Benefits. Then
- list from NICE TO HAVE. Then
- list from What We're Looking For. Then