Research Engineer / Scientist, Reinforcement Learning

The role

You will own the post-training recipe across SFT and RL to improve model capability on long-horizon legal reasoning and agentic workflows. You will design experiments, develop reward functions, and run distributed training at scale.

What you will do

• Own and pursue a research agenda to improve model capability on long-horizon legal reasoning and agentic workflows.
• Design and run post-training experiments across SFT and RL, building on leading open-weight models.
• Develop reward functions and verifiers for semi-verifiable tasks.
• Run and debug training at scale, addressing divergence, reward hacking, and instability.
• Build and use rigorous evals to track improvements and decide what ships.
• Design, implement, test, and debug code across the research stack.

Required qualifications

• Hands-on experience post-training LLMs with SFT and RL, including preference optimization, and direct ownership of training runs and results.
• Deep ML fundamentals and experience getting distributed training runs working reliably.
• Strong engineering skills in Python, with production-quality code and end-to-end system ownership.
• Research experience in RL for language models or reward modeling, with the ability to move quickly from experiments to shipped improvements.

Nice to have

• Publications welcome

About the company

Harvey is transforming how legal and professional services operate by combining frontier agentic AI, an enterprise-grade platform, and deep domain expertise.