Research Engineer: Post-Training LLMs & RL for Legal AI

harvey

United Kingdom

On-site

GBP 90,000 - 150,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Harvey is building an enterprise-grade platform to reshape how legal and professional services operate. As part of Harvey Research, you will own post-training strategies for open-weight models, designing reward models and verifiers to advance legal reasoning and agentic workflows.

You’ll collaborate with a small, high-bar team of engineers and researchers focused on scalable, practical ML for customers. You will influence research directions, run experiments from training to deployment, and

Qualifications

  • Experience post-training LLMs with SFT and RL.
  • Strong ML fundamentals and distributed training experience.
  • Production-quality Python code and end-to-end system ownership.

Responsibilities

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

Skills

Post-training LLMs
SFT & RL
Python
RL for language models

Tools

Python

Job description

Harvey is building an enterprise-grade platform to reshape how legal and professional services operate. As part of Harvey Research, you will own post-training strategies for open-weight models, designing reward models and verifiers to advance legal reasoning and agentic workflows.

You’ll collaborate with a small, high-bar team of engineers and researchers focused on scalable, practical ML for customers. You will influence research directions, run experiments from training to deployment, and

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Engineer - RL for Legal LLMs
Research Engineer - RL for Legal LLMs

Harvey • Greater London

On-site
GBP 110,000 - 180,000
Research Engineer, Data & Evaluations for AI Legal Tech
Research Engineer, Data & Evaluations for AI Legal Tech

Harvey AI • Greater London

On-site
GBP 85,000 - 120,000
Research Engineer / Scientist, Reinforcement Learning
Research Engineer / Scientist, Reinforcement Learning

harvey • United Kingdom

On-site
GBP 90,000 - 150,000
Research Engineer, ML Infra & Distributed Systems
Research Engineer, ML Infra & Distributed Systems

harvey • United Kingdom

On-site
GBP 90,000 - 120,000
Research Engineer / Scientist, Reinforcement Learning
Research Engineer / Scientist, Reinforcement Learning

Harvey • Greater London

On-site
GBP 85,000 - 115,000
Research Engineer / Scientist, Reinforcement Learning
Research Engineer / Scientist, Reinforcement Learning

Harvey • Greater London

On-site
GBP 110,000 - 180,000
Research Engineer / Scientist, Data & Evals
Research Engineer / Scientist, Data & Evals

Harvey • Greater London

On-site
GBP 90,000 - 150,000
Research Engineer / Scientist, Data & Evals
Research Engineer / Scientist, Data & Evals

Speedrun Talent Network • Greater London

Hybrid
GBP 90,000 - 150,000
Research Engineer / Scientist, Data & Evals
Research Engineer / Scientist, Data & Evals

Harvey • Greater London

On-site
GBP 85,000 - 120,000
Research Engineer, ML Infra for Scalable Training
Research Engineer, ML Infra for Scalable Training

Harvey • Greater London

On-site
GBP 100,000 - 160,000