View All Jobs 2626
Research Engineer / Research Scientist, Post - training, Frontier Product Research
Develop novel methods for reward modeling in reinforcement learning environments.
San Francisco, California, United States
Mid-Level
2 weeks ago
✨ About The Role
- The role involves training state-of-the-art models and improving their core capabilities, such as coding and creative reasoning.
- Candidates will design challenging evaluations for novel capabilities and construct reinforcement learning environments.
- The position requires developing scalable synthetic data techniques in reinforcement learning and conducting scientific experiments.
- Collaboration with product, design, and engineering teams is crucial to transition conceptual prototypes into production.
- The job includes iterating on research experiments and clearly communicating insights to the team.
âš¡ Requirements
- The ideal candidate should have a strong technical background in machine learning and artificial intelligence.
- Familiarity with large language models and related infrastructure is essential for success in this role.
- Experience in an applied machine learning setting is highly valued, particularly in product development.
- Strong skills in Python programming are necessary to execute the responsibilities of the position.
- Candidates should be team players, willing to take on a variety of tasks to support team objectives.
Research Engineer / Research Scientist, Post - training, Frontier Product Research
San Francisco, California, United States
Engineering
About OpenAI
Building artificial general intelligence