Skip to content

Research Engineer / Scientist, Reinforcement Learning

HarveySan FranciscoRemote

Estimated salary, not published by the employer: Est. $120k–180k/yr

Needs a free Superjobs account. You'll finish on Harvey's Ashby page.

Skill score

Summary

This role owns post-training of open-weight language models for legal work, covering SFT and RL, reward design and verification, and running training at scale. It suits research engineers and scientists who have run large training jobs and want their work shipped to customers quickly.

Function
Development
Estimated salary
Est. $120k–180k/yr
Estimated for a mid-level role, ~3 yrs experience (typical for the level), United States. Not published by the employer.
Work mode and location
Remote, San Francisco
Employment type
Full-time

Job description

Overview

In this role, you'll own how we adapt and improve leading open-weight models for legal work.

We recently post-trained our first model built for legal work, and we’re now building the team to scale up our post-training efforts. You’ll own the post-training recipe across SFT and RL, including reward design and verification for challenging, semi-verifiable legal tasks. You’ll help set the research direction and carry ideas from experiments through training runs to models used by customers. You’ll join a small, high-bar team of hands-on engineers and researchers, where each person owns a large part of the work.

We’re looking for research engineers and scientists who have gotten training runs working at scale, are immersed in RL for language models, and want their work to reach users quickly.

Roles and 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 required

Top skills

  • LLM post-training
  • SFT
  • Reinforcement learning
  • Preference optimization

All skills (6)

  • Reward modeling
  • Distributed training
  • Python
  • ML fundamentals
  • Model evaluation
  • Reward hacking analysis

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. Publications welcome, not required.

Other details

Learn more about our work at http://harvey.ai/research.

We are hiring for this role across multiple levels.

Compensation

$230,000 - $450,000 USD

Company info

Harvey provides AI software for legal and professional services, with products that streamline workflows such as contract analysis, due diligence, compliance, and litigation. Its products are used by law firms and in-house legal teams around the world.

More jobs at Harvey