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…
Em inglês
- Company
- Harvey
- Location
- London
- Status
- Closed
- Posted
- 2026-10-30 19:47 UTC
Harvey Research is hiring a research engineer or scientist to post-train open-weight language models for legal work. The role covers supervised fine-tuning and reinforcement learning: designing rewards and verifiers for semi-verifiable legal tasks, running and debugging distributed training at scale, and building evaluations that decide what ships. The posting asks for hands-on LLM post-training experience, strong Python engineering, and research background in RL or reward modeling. The team is small and each person owns a large share of the work; hiring spans multiple levels.
Original job posting