T

Applied AI Engineer

The San Francisco Compute Company
3 hours ago
Full-time
On-site
San Francisco, California, United States
About the Tooling Team

We are a small team focused on making SFCompute engineering faster, more observable, and more reliable. Our work spans data infrastructure, developer experience, pre-production environments, and AI tooling β€” but the common thread isn't any specific domain. It's that we find the problems nobody else owns and make them solved problems. Everyone on this team wears many hats. You'll work across the stack, collaborate with all parts of engineering, and regularly take on problems that don't fit neatly into a job description. If you want a narrow scope and a clear ticket queue, this team isn't it. If you want to have a large, legible impact on a small team building serious infrastructure, read on. The Role

We're looking for an Applied AI Engineer to own how AI works for our engineering team. You'll audit how we use tools like Claude Code, identify where AI assistance breaks down or creates friction, and fix it: by writing better skills, rules, and prompts; by improving the context we give AI about our codebase; by changing the workflows that aren't working. This is a new kind of role. It requires someone who thinks rigorously about information flow, understands how large language models reason, and cares enough about developer experience to go fix things rather than just document them. What You'll Do

Audit how engineers across the team use AI tools today β€” what works, what doesn't, where time is lost

Maintain and improve our library of AI skills and rules (the structured context that shapes how AI assists our engineers)

Write high-quality prompts and workflows that reduce toil on common engineering tasks

Identify gaps in our codebase documentation and context that cause AI tools to give poor output

Work directly with engineers to understand their pain points and turn them into systemic improvements

Stay current on AI tooling and evaluate new capabilities as they emerge

Define and track metrics for AI workflow quality and adoption

What We're Looking For

Deep familiarity with AI coding tools (Claude Code, Cursor, Copilot, or similar), not just as a user but as someone who has thought carefully about why they work or don't

Strong writing skills. Prompts and documentation are core outputs of this role.

Engineering background or strong technical fluency. You need to understand the code and workflows you're improving.

Systems thinker. You look for root causes, not just symptoms.

You can run without a spec. The first thing you'll do is figure out what the problems actually are, not execute on a list someone else wrote.

Nice to have: experience with prompt engineering, RAG systems, or developer tooling; familiarity with TypeScript or Rust

Why This Role

This is a new role category and we're not going to pretend we have it fully figured out. What we know: our engineers use Claude Code every day, the quality of that experience varies a lot, and nobody owns fixing it. You will. The impact is immediate. Every engineer on a small team feels it when the tools get better or worse. And what you build here (the skills, the rules, the workflows) is a real artifact, not a presentation deck. Benefits

Team members are offered a competitive salary along with equity in the company Yes, we sponsor visas and work permits We match 401(k) plans up to 4% We offer competitive medical, dental, vision insurance for employees and dependents and cover 100% of premiums We offer unlimited paid time off as well as 10+ observed holidays We offer biological, adoptive, and foster parents paid time off to spend quality time with family We cover lunch daily for employees You can buy as many books for the office as you want The San Francisco Compute Company is committed to maintaining a workplace free from discrimination and harassment. We make employment decisions based on business needs, job requirements, and individual qualifications, without regard to race, color, religion, belief, national origin, social or ethical origin, age, physical, mental, or sensory disability, sexual orientation, gender identity or expression, marital status, civil union or domestic partnership status, past or present military service, HIV status, family medical history or genetic information, family or parental status including pregnancy, or any other status protected by law. We welcome the opportunity to consider qualified applicants with prior arrest or conviction records. Our commitment to diversity includes hiring talented individuals regardless of their criminal history, in accordance with local, state, and federal laws, including San Francisco's Fair Chance Ordinance and California's ban-the-box laws. If you require reasonable accommodation for any reason, please reach out to us at hiring@sfcompute.com