Researcher, Synthetic RL
OpenAI · San Francisco
CHECKED 1H AGO
Frontier labonsite$295k–$445k
At a glance
Highlights
- Develop RL methods using synthetic data and environments for frontier models.
- Explore self-play and simulators to push generalization beyond current methods.
- Translate research insights into production-scale model training pipelines.
What they offer
- Equity
- Relocation assistance
Ideal candidate
RL researcher who thrives on open-ended problems and fast iteration, comfortable with imperfect data and evolving evaluation. Motivated to see novel ideas directly shape frontier model training.
Requirements
- Strong background in reinforcement learning, machine learning research, or related fields
- Strong engineering and statistical analysis skills
- remote policy
- Hybrid - 3 days in office per week
Lab profile
About OpenAI
Builds safe frontier AI models and products like ChatGPT for broad benefit.
What they build
- ChatGPT
- OpenAI API
- Frontier AI models
Known for
- Frontier-scale distributed ML training
- Massive GPU fleet and data center operations
- Exabyte-scale data lakes and streaming
- AI alignment and safety research
Key facts
- Operates one of the world's largest GPU fleets