Remotely
llmdistributed systemsevaluationpromptingretrieval
Job Description
📋 Description
- Own ML projects end-to-end from exploration to production.
- Build agentic LLM systems with tools, retrieval and orchestration.
- Treat evaluation as core engineering work with eval sets and tests.
- Improve model quality via prompting, retrieval, distillation or fine-tuning.
- Work across the full AI stack: data prep, serving, monitoring.
- Partner with Product, Clinical, and Engineering; translate requirements.
🎯 Requirements
- Shipping ML systems to production that users depend on.
- Hands-on LLM work in production: prompting, tool calls, agent workflows.
- Rigorous evaluation: built eval datasets/frameworks.
- Strong ML fundamentals and clear tradeoff reasoning.
- Comfort with ambiguity turning problems into production.
- Solid engineering: production-grade code and distributed systems.
🎁 Benefits
- Exposure to healthcare AI and high-stakes domains.
- Open source contributions and knowledge sharing encouraged.
- Company-wide benefits aligned to local regulations.