Join Harvey as a Research Engineer/Scientist to enhance legal AI models with a focus on reinforcement learning.
Posted by employer 13 hours ago
First seen on Joblaze 3 days ago
Last verified on the company career page 10 hours ago
Skills & Technologies
What you'll build
- Own and pursue a research agenda to improve model capability
- Design and run post-training experiments
- Develop reward functions and verifiers for tasks
- Run and debug training at scale
- Build and use rigorous evals to track improvements
Must have
- Hands-on experience post-training LLMs with SFT and RL
- Deep ML fundamentals
- Strong engineering skills in Python
Nice to have
- Research experience in RL for language models
- Publications welcome
AI in the day-to-day
You'll own how we adapt and improve leading open-weight models for legal work.
Not disclosed in this posting: years of experience, visa sponsorship.
Joblaze summary
In this role, the Research Engineer or Scientist will focus on enhancing legal models through post-training experiments and developing reward functions for complex legal tasks. Key skills include hands-on experience with reinforcement learning and strong engineering capabilities in Python, particularly in managing distributed training runs. This position is suitable for individuals with a solid background in machine learning and a desire to see their research quickly implemented in real-world applications. The team operates at a fast pace, emphasizing ownership and collaboration in a high-expectation environment.
Joblaze insights
- Listed 3 days ago — first seen on Joblaze October 31, 2026. Last confirmed on Harvey's careers page November 3, 2026.
- This exact title is also open at 1 other location at Harvey: London.
- Salary band is above the typical range for AI/ML roles (median ~$190,000).
- Starts above 91% of 152 comparable mid ai/ml roles that list Python we track (median $150,000 across 59 companies). See Python salary trends
- Python appears in 48.2% of 812 comparable mid ai/ml roles; reinforcement learning appears in 5.3% of 812 comparable mid ai/ml roles.
Quick facts
- Is the Research Engineer / Scientist, Reinforcement Learning role remote?
- Yes — Harvey lists this as a fully remote position.
- What's the salary range?
- Harvey lists $230,000–$450,000 for this role.
- What's the tech stack?
- Joblaze extracted these technologies from the posting: Machine Learning, Python, reinforcement learning.
- What seniority level is this role?
- Harvey targets mid-level candidates for this position.
- Is this full-time or contract?
- Full-time for this Research Engineer / Scientist, Reinforcement Learning role at Harvey.
From the original posting
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
#LI-DZ1
Standard company text repeated across Harvey's postings is omitted here.