Researcher, Synthetic RL

Who you are

You have a strong background in reinforcement learning and machine learning research, with a passion for exploring new problem spaces. Your engineering and statistical analysis skills enable you to tackle complex challenges effectively. You enjoy working on open-ended problems and value fast iteration, which is essential for pushing the boundaries of AI model training. You thrive in collaborative environments, working closely with other researchers and engineers to integrate successful approaches into production systems. You are committed to shaping the future of technology through innovative research.

What you'll do

As a Research Scientist on the Synthetic RL team, you will research and develop cutting-edge reinforcement learning algorithms that leverage synthetic data and environments. You will design and run experiments to study training dynamics and model behavior at scale, contributing to the advancement of frontier AI models. Collaborating with engineers and researchers, you will translate research insights into effective training approaches used in production systems. Your work will directly impact how models are trained, pushing the limits of what is possible with current methodologies. You will engage in fast-paced experimentation, iterating on your findings to refine and enhance model capabilities. Your contributions will help drive the development of AI technologies that can address significant global challenges.

What we offer

OpenAI provides a hybrid work model, allowing you to work three days in the office per week while offering relocation assistance for new employees. You will be part of a team that values innovation and collaboration, with opportunities to shape the future of AI. We encourage you to apply even if your experience doesn't match every requirement, as we believe diverse teams build better products. Join us in our mission to ensure that the benefits of AI are widely shared and contribute to impactful technological advancements.