Researcher, Synthetic RL
Core
Develop reinforcement learning techniques using synthetic environments and feedback to improve large-scale frontier AI models.
Role type
Research Scientist (Synthetic RL)
Builds
Novel RL algorithms and training approaches for production systems
Domain
Artificial Intelligence / Reinforcement Learning
Deliverable
production ML models
Required skills
reinforcement learning, machine learning research, statistical analysis, experimental design
Preferred skills
engineering, exploring open-ended problem spaces, fast iteration
Technologies
synthetic environments, simulators, self-play
Responsibilities
Research and develop reinforcement learning algorithms, Design and run experiments to study training dynamics, Collaborate with engineers to integrate approaches into training pipelines
Seniority
Individual Contributor, Research Scientist
Sourced via ashby · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
