Research Engineer / Scientist, Reinforcement Learning

Overview

Harvey is hiring a Research Engineer or Scientist specializing in Reinforcement Learning for the modeling team within Harvey Research. The role is based in London, United Kingdom, and involves transforming how legal and professional services operate by adapting and improving leading open-weight models for legal work.

What you get

Selected candidates join a small team of hands-on engineers and researchers where each individual owns a large part of the work. Visa sponsorship may be offered for suitable candidates.

Requirements

Applicants need hands-on experience post-training large language models with supervised fine-tuning and reinforcement learning, including preference optimization and direct ownership of training runs and results. Candidates must have deep machine learning fundamentals, experience getting distributed training runs working reliably, and strong engineering skills in Python with production-quality code and end-to-end system ownership. Research experience in reinforcement learning for language models or reward modeling is required, along with the ability to move quickly from experiments to shipped improvements.

How to apply

Applications are accepted for multiple levels of this role.