Staff RL Scientist - Healthcare AI

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

Job summary

Hippocratic AI is seeking experts to own the Reinforcement Learning (RL) and On-Policy Distillation (OPD) post-training pipeline for healthcare LLMs. You will improve clinical reasoning, safety, and alignment, deploying models to interact with millions of patients across diverse clinical use cases.

The role requires 5+ years in NLP, LLM training, or RL, with 2+ years in RL for LLM post-training, and hands-on experience with large-scale multi-node LLMs in a Palo Alto setting.

Qualifications

• Requires MS/PhD in CS or related field and strong background in NLP, RL, and ML.
• Proficiency in Python and PyTorch with experience in large-scale LLM training.
• Experience with RLHF, RLVR, and post-training methods for LLMs.

Responsibilities

• Design RL and OPD post-training methods (RLHF, RLVR, OPD) for healthcare LLMs.
• Build and evaluate reward models, verifiers, and LLM-as-judge pipelines.
• Develop conversational AI environments and simulations for RL training with synthetic data.
• Automate post-training loops with agents and automate experiments.
• Run rigorous experiments to understand drivers of post-training gains.
• Collaborate with research, engineering, and clinical teams.

Skills

Python

PyTorch

NLP

RL training

RLHF/RLVR

Education

MS or PhD in CS or relevant field

Tools

PyTorch (distributed)

Job description

Hippocratic AI is seeking experts to own the Reinforcement Learning (RL) and On-Policy Distillation (OPD) post-training pipeline for healthcare LLMs. You will improve clinical reasoning, safety, and alignment, deploying models to interact with millions of patients across diverse clinical use cases.

The role requires 5+ years in NLP, LLM training, or RL, with 2+ years in RL for LLM post-training, and hands-on experience with large-scale multi-node LLMs in a Palo Alto setting.