About the role
You will design the AI side of our builds: knowledge assistants with citations, agents that draft and sort, and LLM features inside client products. We care more about an assistant that says 'I don't know' than one that sounds confident and is wrong.
What you will do
- Build retrieval pipelines over PDFs, Drive, Notion and code with PostgreSQL and pgvector
- Design prompts and structured outputs for Claude, GPT and Gemini
- Create evaluation sets from real client data and run them on every change
- Set cost and latency limits, caching and fallbacks between providers
- Explain trade-offs to clients in plain language
What we are looking for
- 2+ years of Python in production
- Shipped at least one LLM feature used by real people
- Understanding of embeddings, chunking and retrieval quality
- Habit of measuring before and after a change
Nice to have
- FastAPI
- LangGraph or the OpenAI Agents SDK
- Model Context Protocol (MCP)
How hiring works
- 1. ApplyYour CV and a few lines about something you built. About five minutes.
- 2. Intro callA 30-minute conversation with Kishan about the role and how you like to work.
- 3. Practical taskA small task based on real work, scoped together so it fits around your week.
- 4. DecisionWe tell you either way, with a reason. Everyone who applies gets a reply.