Research Engineer, RL Scaling Science
Core
Design and run large-scale reinforcement learning experiments to understand scaling behaviors and resolve bottlenecks, translating validated findings into production training recipes for frontier AI models.
Role type
Research Engineer, RL Scaling Science
Builds
Benchmarks for long-horizon RL and production training recipes
Domain
Artificial Intelligence, Reinforcement Learning, Large-scale ML
Deliverable
production ML models
Required skills
Empirical research in Reinforcement Learning, End-to-end experiment ownership, Python proficiency, Large-scale/distributed ML systems experience, Debugging research-infrastructure interfaces
Preferred skills
Published/shipped work in long-horizon RL, Experience translating research to production, Large-scale industry impact via RL, Frontier-scale training run experience
Technologies
Python, Distributed ML systems
Responsibilities
Design, run, and interpret large-scale RL experiments; Investigate RL improvements with growing horizon, compute, and model size; Build and maintain benchmarks for long-horizon RL; Translate validated findings into production training recipes; Debug complex issues at the research-infrastructure seam; Partner with adjacent RL teams to advance the RL stack
Seniority
Mid-to-Senior, hands-on IC
