
Research Engineer / Scientist, Reinforcement Learning
AI
Harvey is hiring a Research Engineer / Scientist for Reinforcement Learning to own post-training of open-weight LLMs for legal work. The role involves SFT and RL, reward design and verification, and scaling training runs. Candidates need hands-on LLM post-training experience, deep ML fundamentals, and strong Python engineering skills.
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
What you need
Must-have
Reinforcement LearningSupervised Fine-TuningPreference OptimizationReward ModelingLarge Language ModelsMachine LearningDistributed TrainingPythonEvaluation
Soft skills
OwnershipDecisivenessSimplicityHands-onResearch
Reinforcement LearningLLMPost-trainingLegal TechAI ResearchPythonMachine LearningLondonHybrid