Research Engineer / Scientist, Reinforcement Learning

Harvey; New York (NY); On-site; USD 230,000 - 450,000; Full time

Job summary

Harvey is building leading open-weight models for legal work and scaling a post-training workflow that includes SFT and RL. You’ll own the recipe across training stages, help set the research direction, and work with a tight, hands-on team of engineers and scientists.

You’ll design reward functions, verifiers, and evaluation protocols, ensuring robust results reach customers quickly. This role offers high impact, growth potential, and a fast-moving environment at Harvey.

Qualifications

• Experience in post-training LLMs with SFT/RL and managing training runs.
• Distributed training experience and reliability.
• Proficiency in Python with production-quality code.
• RL for language models or reward modeling research experience.

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 and preference data.
• 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

ML fundamentals

Python engineering

RL for LMs

Job description

Why Harvey

At Harvey, we’re transforming how legal and professional services operate. By combining frontier agentic AI, an enterprise-grade platform, and deep domain expertise, we’re reshaping how critical knowledge work gets done for decades to come.

Why Harvey

At Harvey, we’re transforming how legal and professional services operate. By combining frontier agentic AI, an enterprise-grade platform, and deep domain expertise, we’re reshaping how critical knowledge work gets done for decades to come.

This is a rare chance to help build a generational company at a true inflection point. We have strong product-market fit and world-class investor support. We’re scaling fast and defining a new category in real time. The work is ambitious, the bar is high, and the opportunity for growth — personal, professional, and financial — is unmatched.

Our team moves fast, takes ownership, and is deeply committed to the mission — operating with intensity, staying close to our customers, and pushing each other for excellence. We live by three values: Decisiveness, Simplicity, and Job's Not Finished. We act quickly on clear judgment over perfect information, we believe simplicity is what scales, and we're never satisfied with where we are. If you want to do the best work of your career alongside people who share that drive, we'd love to build with you.

At Harvey, the future of professional services is being written today — and we’re just getting started.

Role Overview

As a Member of Technical Staff, Modeling in Harvey Research, 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.

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

What You'll Do

• 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.

What You Have

• 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.

We are hiring for this role across multiple levels.

Compensation

$230,000 - $450,000 USD

Depending on your location, an Applicant Privacy Notice may apply to you. You can find all of our Applicant Privacy Notices here.

Harvey is an equal opportunity employer and does not discriminate on the basis of race, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition, or any other basis protected by law.

We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made by emailing [e-mail]