Senior Applied Scientist (Reinforcement Learning)

Join our team as a Senior Applied Scientist specializing in Reinforcement Learning. In this role, you will be responsible for improving our models' clinical reasoning, safety, and alignment through the development and implementation of post-training methods. Your work will have a direct impact on millions of patients across diverse clinical use cases. You will collaborate with research, engineering, and clinical teams, and have the opportunity to work with cutting-edge technology in the healthcare industry.

Responsibilities

• Ownership of the Reinforcement Learning (RL) and On-Policy Distillation (OPD) post-training pipeline to enhance clinical reasoning and safety.
• Designing and implementing RL and OPD post-training methods, including RLHF, RLVR, and OPD.
• Building and evaluating reward models, verifiers, and LLM-as-judge pipelines to improve model performance.

Requirements

• Experience with RLHF, RLVR, LLM-as-judge or similar methods for LLM post-training

Strong Python and PyTorch coding skills

• 3+ years or experience in NLP, LLM training, or RL
• Experience with large-scale (50B+ parameter and multi-node) LLM training
• 1+ years experience in RL for LLM post-training
• MS or PhD in CS or relevant field