jobs
Research Engineer / Scientist, Reinforcement Learning
Why HarveyAt Harvey, we’re transforming how legal and professional services operate. By combining frontier agentic AI, an enterprise-grade platform, and deep domain expertise, we’re reshaping how…
En anglais
- Company
- Harvey
- Location
- San Francisco
- Status
- Open
- Posted
- 2026-11-02 21:04 UTC
Harvey Research is hiring a Member of Technical Staff, Modeling to own post-training of open-weight models for legal work. The role covers the SFT and RL recipe: designing experiments, writing reward functions and verifiers for semi-verifiable legal tasks, running and debugging distributed training, and building evals that decide what ships. Candidates need hands-on LLM post-training experience, RL or reward-modeling research, and production-quality Python. Harvey recently post-trained its first legal model and is scaling that effort with a small, high-bar team; hiring spans multiple levels.
Original job posting