Research Engineer - RL for Legal LLMs

Harvey; Greater London; On-site; GBP 110,000 - 180,000; Full time

Job summary

Harvey is building cutting-edge AI for legal work. As a Member of Technical Staff, Modeling, you will shape post-training recipes across SFT and RL, and own reward design and verification for challenging tasks.

You will join a small, high-bar team of engineers and researchers who own a large portion of the work, with opportunities to impact customers and products. We hire across multiple levels and emphasize decisiveness, simplicity, and ownership.

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.

Responsibilities

• 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, including rubrics, learned preference models, and expert preference data, and study where they break.
• 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 our research stack.

Skills

LLM Training

RL for LLMs

Python programming

Distributed training

Research experience

Job description

Harvey is building cutting-edge AI for legal work. As a Member of Technical Staff, Modeling, you will shape post-training recipes across SFT and RL, and own reward design and verification for challenging tasks.

You will join a small, high-bar team of engineers and researchers who own a large portion of the work, with opportunities to impact customers and products. We hire across multiple levels and emphasize decisiveness, simplicity, and ownership.