We hire experienced engineers when we meet the right people, rather than to fill a fixed list of openings. If you have shipped software that real users depend on and want to build AI systems for enterprises, we would like to hear from you.
- LLM orchestration with LangGraph — multi-step agents, tool calling, and the state machines that keep them predictable.
- RAG and vector retrieval — chunking, embeddings, and measuring whether retrieval returns the right thing.
- Evals — deciding whether a change made the system better, with evidence rather than instinct.
- Real-time voice — streaming speech in and out, inside a latency budget a caller will tolerate.
- AWS infrastructure — the deployment path that puts your work in front of customers.
Most of this is ordinary software engineering — clean Python, sensible structure, tests, review, deployments. The AI sits on top of a well-built codebase, and the codebase is the part that has to be right.
What we look for
Software you have shipped that real users depend on.
Hands-on work with LLMs in a real system, not a demo.
Strong Python, and code you can explain line by line.
Cloud comfort — AWS ideally; any cloud counts.
Before you apply
Are you hiring for specific roles?
We hire when we meet the right people rather than to fill a fixed list of openings. If your experience fits what is on this page, send us your CV — we read every one.
What experience do you look for?
Software you have shipped that real users depend on, and hands-on work with LLMs in a real system rather than a demo. We care more about what you built and how you reasoned about it than about job titles.
How to apply
By email, with links to anything you have built.
Mostly you walking us through something you made. Terms are discussed here.
You see the scope and what done looks like before you commit to anything.
Reviewed, tested and running in a product people use.