OpenAI
Research Engineer/Research Scientist, RL/Reasoning
$295K–$445K
San Francisco · Full-time · Posted May 14, 2025
About the job
Advance reinforcement learning methods for training intelligent, aligned, general-purpose agents and language models.
What you'll do
- Conduct reinforcement learning research and develop cutting-edge RL methods.
- Build, debug, and improve machine-learning code and systems.
- Rapidly iterate on experiments and help train and deploy models at scale.
What they ask for
- Background in reinforcement learning research.
- Proficient coding skills.
- Deep understanding of machine learning and its applications.
- Ability to work in a large ML codebase and iterate quickly.
Nice to have
Pay
$295K – $445K (base salary)
Tools
reinforcement learning, language models, ML codebase
AI focus
Research and develop RL methods for AI alignment and capabilities, reasoning, and training general-purpose agents and generative models.
Model-written summary · the original posting is authoritative