ml engineer for legal work

Harvey combines agentic AI, an enterprise-grade platform, and domain expertise to transform legal and professional services.

• Own and pursue a research agenda to improve model capability in 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, including rubrics, learned preference models, and expert preference data, and study their limitations
• Run and debug training at scale, addressing divergence, reward hacking, and instability
• Build and use rigorous evaluations to track improvements and decide what ships
• Design, implement, test, and debug code across the research stack

• 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 Python engineering skills, production-quality coding, 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
• Publications are welcome but not required

• Equity offered
• Bonus offered