Applied Scientist, Reinforcement Learning (Mid, Senior, Staff)
Hippocratic AI· R&D
Menlo Park, CAFull-timePosted 2mo ago
About the role
Role focused on owning the reinforcement learning and on-policy distillation pipeline for healthcare AI post-training to transform model capability into reliable, safe clinical behavior, with emphasis on clinical reasoning, safety alignment, and production impact.
Responsibilities
- Design and implement RL and OPD post-training methods including RLHF, RLVR, on-policy distillation, and healthcare-tailored approaches
- Build and evaluate reward models, verifiers, and LLM-as-judge pipelines for reliable training signals in clinical contexts
- Develop conversational AI environments and simulations for safe, scalable healthcare RL training
- Automate post-training research loops using agents and tooling to make post-training a reproducible process
- Run rigorous experiments and analysis to understand drivers of post-training gains and component contributions
- Collaborate with research, engineering, and clinical teams to translate requirements into post-training objectives and scale methods to production
Qualifications
- Master's degree in Computer Science, Machine Learning, or a related field
- 5+ years of professional experience in NLP, LLM training, or reinforcement learning
- 2+ years of hands-on experience with RL for LLM post-training
- Proficiency in Python and PyTorch for large-scale training
- Demonstrated experience with RLHF, RLVR, LLM-as-judge, or similar post-training methods
- Experience training or fine-tuning models at scale (50B+ parameters)
Skills
Required:RL and OPD post-training methods (RLHF, RLVR, on-policy distillation)Reward models, verifiers, LLM-as-judge pipelinesConversations AI environments and simulationsExperimentation and analysisCollaboration with multi-disciplinary teams
Benefits
- Competitive base salary and stock options (compensation package described)
Last updated Sep 30, 2026. Interested? Apply on the company site.
About Hippocratic AI
Safest Healthcare Generative AI Agents
Safest Healthcare Generative AI Agents Our AI agents do not diagnose or prescribe. Learn more. Listen to these 4 real de-identified calls from the over 115 million clinical interactions.
HealthcareAIGenerative AIClinical InteractionsPatient Care
More open roles at Hippocratic AI
- Technical Program Manager - Frontier AI Data Labeling4d agoMenlo Park, CA · R&D
- Governance Risk Compliance4d agoMenlo Park, CA · G&A
- Lead Product Data Analyst4d agoMenlo Park, CA · R&D
- Deployment Strategist (Payors)1w agoRemote · C&S
- Accounting Manager1w agoGurugram, India · G&A