About the role
You own features whole: the retrieval and orchestration behind them, the API they expose, and the interface a customer touches. Most of our surface area is agent tooling used by people who will notice the moment an answer is wrong, so correctness and legibility matter more than volume of code.
What you’ll do
Ship GenAI features end to end, from data layer to UI
Design and tune retrieval, prompting and tool-calling flows
Write the evaluations that prove a change made answers better
Work directly with customers' engineers during rollouts
What we need
2 to 8 years building production web applicationsStrong Python and TypeScriptHands-on with LLM APIs, embeddings and vector searchComfortable owning a feature without a spec handed to you
Nice to have
Experience in a regulated environmentStreaming UIs and websocket-heavy interfacesOpen-source contributions in the LLM tooling space
How hiring works
1Intro call, 30 minutesWhat you have shipped, what you want next, and an honest picture of where we are as a company.
2Working sessionA real problem from our backlog, discussed or built together. No whiteboard algorithm puzzles.
3Team conversationsTwo calls with the people you would work with daily, across both regions.
4Offer within a weekDecision and written offer inside five working days of the last call, references in parallel.
Ready to apply?
Send a CV or a link to something you’ve shipped. A short note on why this role beats a paragraph of cover letter.