About the role
Design, build, and deploy production AI systems — agents, fine-tuned models, and inference pipelines serving enterprise clients globally.
You'll work across the full AI delivery lifecycle, from architecture and prototyping through to production monitoring and iteration.
We expect you to be comfortable with LangChain, the Anthropic / OpenAI APIs, vector databases, and the engineering tradeoffs between agent designs. You'll partner with our context engineers, our infra team, and our delivery leads on real client work.
What we're looking for
- 3+ years building backend systems (Python, TypeScript, or Go)
- Production experience with at least one major LLM provider
- Comfortable with retrieval-augmented generation, evaluation, and observability
- English-first written communication