LLM Post-training Engineer (AI)

TL;DR

LLM Post-training Engineer (AI): Designing and owning the RL and OPD post-training pipeline for a healthcare-focused LLM with an accent on clinical reasoning, safety, and alignment. Focus on building reward models, verifiers, and conversational AI simulations to ensure high-accuracy patient interactions.

Location: On-site in Palo Alto, CA (5 days a week)

Company

Hippocratic AI is a generative AI company developing the first safety-focused LLM specifically for healthcare to improve patient outcomes globally.

What you will do

• Design RL and OPD post-training methods such as RLHF and RLVR.
• Build and evaluate reward models, verifiers, and LLM-as-judge pipelines.
• Develop conversational AI environments and simulations for healthcare RL training using synthetic data.
• Automate post-training loops utilizing agents for auto-research.
• Execute rigorous experiments to determine drivers of post-training gains.
• Collaborate with research, engineering, and clinical teams.

Requirements

• MS or PhD in Computer Science or a relevant field.
• 3+ years of experience in NLP, LLM training, or RL.
• 1+ years of experience specifically in RL for LLM post-training.
• Experience with large-scale LLM training (50B+ parameters and multi-node).
• Strong proficiency in Python and PyTorch.
• Experience with RLHF, RLVR, LLM-as-judge, or similar post-training methods.

Culture & Benefits

• Work with a world-class team of AI pioneers, physicians, and researchers.
• Backed by leading investors including Avenir Growth, CapitalG, and a16z.
• Involved in category creation by building a world-first healthcare-only LLM.
• Fast-paced, collaborative environment with a strong on-site team culture.