Researcher, Synthetic RL

OpenAI OpenAI · AI Frontier · San Francisco, CA · Research

Research Scientist role focused on developing novel reinforcement learning techniques using synthetic data, environments, and feedback to train and evaluate frontier AI models, with a focus on generalization and alignment. The role involves designing experiments, analyzing training dynamics, and integrating research into production pipelines.

What you'd actually do

  1. Research and develop reinforcement learning algorithms
  2. Design and run experiments to study training dynamics and model behavior at scale
  3. Collaborate with engineers and researchers to integrate successful approaches into model training pipelines

Skills

Required

  • reinforcement learning
  • machine learning research
  • statistical analysis

Nice to have

  • engineering skills
  • experience with synthetic data
  • experience with AI alignment

What the JD emphasized

  • novel reinforcement learning techniques
  • synthetic data
  • frontier AI models
  • model capability
  • generalization
  • alignment
  • research insights into training approaches used in production systems
  • open-ended problems
  • fast iteration
  • directly shape how frontier models are trained
  • strong background in reinforcement learning
  • machine learning research
  • engineering and statistical analysis skills
  • exploring new problem spaces where data, objectives, and evaluation are imperfect or evolving
  • motivated by seeing research ideas influence real-world AI systems

Other signals

  • reinforcement learning
  • synthetic data
  • frontier AI models
  • model alignment