Research Engineer, RL Scaling Science

As a Research Engineer on Anthropic’s RL Scaling Science team, you design and run large-scale RL experiments to understand how horizon, compute, and model size affect performance. You translate findings into production training recipes, bridging research and engineering at frontier scale. You’ll build benchmarks for long-horizon RL and collaborate across RL teams to drive measurable, responsible advancements. You join a mission-driven, collaborative environment that values empirical rigor and impactful AI at scale.

• competitive compensation
• optional equity donation matching
• generous vacation and parental leave
• flexible working hours
• lovely office space

• Design, run, and interpret large-scale RL experiments to rigorously evaluate data signals
• Explore how RL performance scales with horizon, compute, and model size
• Build and maintain benchmarks for long-horizon RL to enable measurable progress
• Translate validated findings into production training recipes and assess robustness
• Debug scale-specific failures at the research-infrastructure seam
• Collaborate with adjacent RL teams to advance the overall RL stack

• Strong empirical RL research skills or closely related领域
• Ability to own large experiments end-to-end from design to interpretation
• Proficiency in Python and experience with large-scale or distributed ML systems
• Comfort operating at the research/systems boundary and debugging at scale
• Concern for societal impacts and responsible scaling

• Strong collaboration and communication across research and engineering
• Problem-solving mindset and rigor in interpretation of results
• Adaptability to frontier-scale, open-ended problems
• Python proficiency
• Experience with large-scale or distributed ML systems
• Experience translating research findings into production training recipes