Researcher, Synthetic RL

📋 Description

• Develop novel reinforcement learning techniques using synthetic environments and feedback.
• Design and run experiments to study training dynamics and model behavior at scale.
• Collaborate with engineers/researchers to integrate approaches into training pipelines.

🎯 Requirements

• Strong background in reinforcement learning, ML research, or related fields.
• Strong engineering and statistical analysis skills.
• Enjoy exploring open-ended problems where data and objectives evolve.
• Motivated by seeing research ideas influence real-world AI systems.

🎁 Benefits

• Hybrid work: 3 days in-office per week.
• Relocation assistance for new employees.
• Based in San Francisco, CA.