OpenAI
Researcher, Synthetic RL
$295K–$445K
San Francisco · Full-time · Posted Jan 9, 2026
About the job
Develop reinforcement learning methods using synthetic environments and feedback to improve large-scale models, and translate research into production training approaches.
What you'll do
- Research and develop reinforcement learning algorithms.
- Design and run experiments studying training dynamics and model behavior at scale.
- Collaborate with engineers and researchers to integrate successful methods into model-training pipelines.
What they ask for
- Strong background in reinforcement learning, machine learning research, or a related field.
- Strong engineering and statistical analysis skills.
Pay
$295K – $445K USD base salary
AI focus
Research reinforcement learning using synthetic data, environments, and feedback to train and evaluate frontier AI models, with applications to capability, generalization, and alignment.
Model-written summary · the original posting is authoritative