H
Research Engineer / Scientist, Reinforcement Learning
Contract type
Ongoing
Work mode
Remote
Experience
3 years
Job description
Member of Technical Staff, Modeling in Harvey Research, owning post-training of leading open-weight models for legal work. The role involves setting research direction and carrying ideas from experiments through training runs to customer-facing models.
At a glance
- Work mode
- Remote
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 we're looking for
- 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
Nice to have
- Publications welcome, not required
Your team
Harvey Research
A small, high-bar team of hands-on engineers and researchers, where each person owns a large part of the work.
Benefits
- Offers Equity
- Offers Bonus
Apply
About Harvey
Harvey is building a generational company at a true inflection point, with strong product-market fit and world-class investor support, scaling fast and defining a new category in real time.
Mission
Transforming how legal and professional services operate by combining frontier agentic AI, an enterprise-grade platform, and deep domain expertise.
Key facts
- Recently post-trained its first model built for legal work
- Hiring for this role across multiple levels
What they value
- Decisiveness
- Simplicity
- Job's Not Finished