Senior RL Scientist - Healthcare AI Safety

Hippocratic AI Inc.; Menlo Park (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Hippocratic AI in Menlo Park seeks a highly skilled researcher to own the RL and OPD post-training pipeline end to end. You will improve models’ clinical reasoning, safety, and alignment as they interact with millions of patients across diverse clinical use cases.

Applicants should have 3+ years in NLP/LLM training or RL, 1+ year in RL for LLM post-training, and strong Python/PyTorch skills. Experience with RLHF, RLVR, or LLM-as-judge is required to contribute to our safety-first healthcare

Qualifications

• MS or PhD in CS or relevant field is required.
• 3+ years of experience in NLP, LLM training, or RL.
• 1+ 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.

Responsibilities

• 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 drivers of post-training gains.
• Collaborate with research, engineering, and clinical teams.

Skills

NLP

RL

Python

PyTorch

LLM training

Cross-functional collaboration

Education

MS or PhD in CS or relevant field

Tools

PyTorch

Distributed training

Job description

Hippocratic AI in Menlo Park seeks a highly skilled researcher to own the RL and OPD post-training pipeline end to end. You will improve models’ clinical reasoning, safety, and alignment as they interact with millions of patients across diverse clinical use cases.

Applicants should have 3+ years in NLP/LLM training or RL, 1+ year in RL for LLM post-training, and strong Python/PyTorch skills. Experience with RLHF, RLVR, or LLM-as-judge is required to contribute to our safety-first healthcare