← All roles
EngineeringRemote / SFFull-timeSenior
ML / AI Engineer
Design and optimize our RAG pipelines, embedding models, and LLM orchestration layer. Deep experience with retrieval systems required.
About the role
Own the AI router, the engine registry, evals, and the fine-tuning stack. Ship measurable improvements to latency, cost, and quality — weekly.
What you'll do
- Improve the multi-provider AI router (Groq / Anthropic / OpenAI / local)
- Build evals and dashboards to track model quality across 30 products
- Own RAG pipelines, embeddings, and retrieval quality
- Contribute to agent orchestration and tool-use reliability
What you bring
- Strong Python, deep familiarity with modern LLM APIs
- Experience shipping production RAG or retrieval systems
- Working knowledge of vector stores, embeddings, and chunking strategies
- Ability to reason about cost and latency trade-offs
Compensation
Competitive salary + meaningful equity.
Apply
Send a short note — what you'd build, and a link to your best work. No cover letters.
Not the right role? See all openings.