Research Engineer (RL Scaling Science)

Join Anthropic's RL Scaling Science team as a Research Engineer. You'll design and run large-scale experiments to understand and resolve bottlenecks in reinforcement learning, build benchmarks for long-horizon progress, and translate validated findings into production training. This role combines research and engineering, with a focus on large-scale experiments and production implementation.

• Design and run large-scale experiments to understand and resolve bottlenecks in reinforcement learning.
• Build and maintain benchmarks for long-horizon reinforcement learning to ensure progress is measurable and reproducible.
• Translate validated findings from experiments into production training recipes, exercising judgment about when a result is robust enough to ship.
• Strong empirical research skills in Reinforcement Learning, large-scale ML training, or a closely adjacent area
• Demonstrated ability to own large experiments end-to-end, from design through interpretation
• Comfort operating at the research/systems boundary, including debugging where the two meet
• Care about the societal impacts of AI and responsible scaling
• Proficiency in Python and experience working with large-scale or distributed ML systems
• Experience translating research findings into production training recipes
• Published or shipped work in long-horizon RL or RL fundamentals
• Demonstrated large scale industry impact via RL interventions
• Experience working on frontier-scale training runs with long trajectories
• Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience
• Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience
• Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position
• We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed