jobs

Research Engineer/Research Scientist, RL/Reasoning

OpenAI’s RL and Reasoning team works on reinforcement-learning research, next-generation generative models, and deploying these systems at scale. The team describes its work as advancing the core reasoning paradigm and developing systems th

Company

OpenAI

Location

San Francisco, United States

Status

Closed

Posted

2026-09-25T03:33:26.885+00:00

OpenAI's RL and Reasoning team works on reinforcement-learning research, generative models, and deploying those systems at scale. The hire contributes to alignment and capability work using RL methods, close to model and agent training, moving between research ideas, experiments, and implementation. The posting asks for a background in reinforcement-learning research, fast iteration, strong coding, and comfort working in a large machine-learning codebase. It lists a $295,000–$445,000 base salary plus equity, hybrid work in San Francisco with three office days, and relocation assistance.