Back to all roles
AI Engineer
You'll build and ship production AI agents that do real work: tool use, retrieval, evals, and monitoring, wired into systems people depend on. This is hands-on product engineering, not research. You'll own features from the first sketch to the thing running in production, and you'll have room to decide how it's built.
What you’ll do
- Design and ship LLM-backed features end to end, from prompt and tool design through API, data, and UI.
- Build the unglamorous parts that make agents trustworthy: evals, guardrails, retries, observability.
- Own delivery. Scope the work, make the calls, and get it in front of users.
- Review other people’s code and take reviews on your own. Craft is a team habit here.
What we’re looking for
- 2+ years shipping production software, with real time spent on LLM-backed systems.
- Comfortable across the stack: TypeScript or Python, an API layer, a database, and a front end.
- You’ve debugged a model in production, not just a notebook.
- Clear writing and clear thinking. You can explain a tradeoff without hand-waving.
Nice to have
- Experience with evals frameworks, RAG at scale, or agent orchestration.
- You’ve run something you built in front of paying users.
- Open-source work we can look at.