openai
Research Engineer/Research Scientist, RL/Reasoning
San Franciscofulltimemid
About this role
Join OpenAI's RL and Reasoning team to advance AI alignment and capabilities through cutting-edge reinforcement learning methods. You'll contribute to training intelligent, aligned agents and help push the boundaries of generative models like o1 and o3.
What you'll do
- Advance AI alignment and capabilities through reinforcement learning research
- Develop and improve RL methods for training general-purpose agents
- Debug and enhance large-scale ML codebases
- Design and run principled experiments in controlled settings
- Iterate quickly on research ideas from conception to completion
- Contribute to deploying next-generation models at scale
What they're looking for
- Reinforcement learning research
- Machine learning fundamentals and applications
- Proficient coding ability
- Rapid iteration and experimentation
- Large codebase debugging and optimization
- Principled experimental design
- Self-direction and ownership
- Experience with language models or generative AI
Benefits
- Work on cutting-edge RL and language model research
- Hybrid work model (3 days per week in office)
- Based in San Francisco, CA
- Relocation assistance provided
- Collaborate with world-leading AI researchers
Opens the official application on the employer’s site. No login required.