← All open roles
Engineeringfull-timeRemote-friendly
AI Engineer
Help us build production LLM applications for enterprise clients. You'll own retrieval pipelines, evals, agent orchestration, and the systems engineering that makes AI features actually shippable.
Remote 3+ years Remote ok Posted April 28, 2026
What you'll do
- Design and implement retrieval pipelines over private corpora
- Build eval harnesses and own quality metrics
- Integrate LLM features into existing client products
- Track cost, latency, and quality in production
- Stay current with model releases and tooling
What we're looking for
- 3+ years engineering experience, with at least 1 year shipping LLM features
- Strong Python; comfort with TypeScript a plus
- Familiarity with vector databases and retrieval techniques
- Production debugging chops — tracing, profiling, observability
Nice to have
- Experience with Claude, OpenAI, or open-source models in production
- Background in NLP, ML, or applied research