Hippocratic AI
Senior Applied Scientist, Reinforcement Learning
Menlo Park, CA · On-site · Senior · Full-time · Posted Oct 27, 2026
- Experience
- 3+ years of experience in NLP, LLM training, or RL; 1+ years of experience in RL for LLM post-training.
- Education
- MS or PhD in CS or relevant field.
About the job
Own the reinforcement learning and on-policy distillation post-training pipeline to improve healthcare LLMs’ clinical reasoning, safety, and alignment.
What you'll do
- Design RL and OPD post-training methods and build reward models, verifiers, and LLM-as-judge pipelines.
- Develop simulated healthcare conversational environments for RL training and automate post-training loops with agents.
- Run experiments and collaborate with research, engineering, and clinical teams.
What they ask for
- MS or PhD in CS or a relevant field.
- Experience with large-scale (50B+ parameter and multi-node) LLM training.
- Strong Python and PyTorch coding skills.
- Experience with RLHF, RLVR, LLM-as-judge, or similar LLM post-training methods.
Tools
Python, PyTorch, RLHF, RLVR, OPD
AI focus
Develop and post-train healthcare LLMs using reinforcement learning and on-policy distillation, focusing on clinical reasoning, safety, and alignment.
Model-written summary · the original posting is authoritative