6h ago

Researcher, Synthetic RL

San Francisco, CA

$295k-$445k / year

full-timesenior Hybridai-ml

💼 About This Role

You'll develop novel reinforcement learning techniques using synthetic environments and feedback to improve large-scale AI models. Your work will directly shape how frontier models are trained and deployed in production systems.

🎯 What You'll Do

  • Research and develop reinforcement learning algorithms.
  • Design and run experiments to study training dynamics at scale.
  • Collaborate on integrating successful approaches into training pipelines.

📋 Requirements

  • Strong background in reinforcement learning or machine learning research.
  • Strong engineering and statistical analysis skills.
  • Ability to explore new problem spaces with imperfect data and objectives.

✨ Nice to Have

  • Experience with large-scale model training.
  • Published research in RL or related fields.

🎁 Benefits & Perks

  • 💰 Equity included in compensation.
  • 🏢 Hybrid work model (3 days in office).
  • 🚚 Relocation assistance available.
0 0 0