Location RequirementWe believe the best ideas happen together. To support fast collaboration and a strong team culture, this role is expected to be in our Palo Alto office five days a week, unless otherwise specified.
About the RoleLLM post-training is where raw capability becomes reliable, safe behavior - and in healthcare, the stakes are as high as they get. You'll own the Reinforcement Learning (RL) and On-Policy Distillation (OPD) post-training pipeline end to end, to improve our models' clinical reasoning, safety, and alignment. Your models will be deployed to interact with millions of patients across diverse clinical use cases.
What You'll Do- Design RL and OPD post-training methods (RLHF, RLVR, OPD, etc.)
- Build and evaluate reward models, verifiers, and LLM-as-judge pipelines
- Develop conversational AI environments and simulations for healthcare RL training with synthetic data
- Automate post-training loops with agents (auto-research)
- Run rigorous experiments to understand what drives post-training gains
- Collaborate with research, engineering, and clinical teams
What You Bring- MS or PhD in CS or relevant field
- 5+ years or experience in NLP, LLM training, or RL
- 2+ years experience in RL for LLM post-training
- 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 methods for LLM post-training
Nice-to-Have:
- Publications at top venues (NeurIPS, ICML, ICLR, ACL, EMNLP)
- Healthcare domain experience
Please be aware of recruitment scams impersonating Hippocratic AI. All recruiting communication will come from [redacted].com email addresses. We will never request payment or sensitive personal information during the hiring process.
