About The Role You will work directly with the founders on the AI core that powers both client engagements and our own products. This is hands-on, end-to-end engineering: from prototyping a pipeline to running it in production with the evals and guardrails to keep it honest.
What you'll do
- Build LLM applications: retrieval, tool-using agents, orchestration and memory.
- Stand up evaluation and observability so quality is measured, not assumed.
- Take ownership of latency, cost and reliability in production.
- Work across the stack to expose models through clean, well-documented APIs.
What we're looking for
- Strong Python and solid software-engineering fundamentals.
- Hands-on experience with LLM apps (agents, or fine-tuning) shipped to real users.
- Comfort with cloud, containers and CI — you can deploy what you build.
- A bias to ship and the judgement to know when something is valuable enough.
Nice to have
- Experience with speech or multimodal systems.
- Open-source contributions or published work.
Ready to apply? Takes about five minutes. Apply for this role →