Research Engineer, RL Scaling Science

Overview

Research Engineer for Anthropic’s RL Scaling Science team, focused on understanding and scaling reinforcement learning and turning results into production training recipes.

What you'll do

• Design, run, and interpret large-scale RL experiments.
• Investigate how RL improves as horizon, compute, and model size grow.
• Build and maintain long-horizon RL benchmarks for measurable, reproducible progress.
• Translate validated findings into production training recipes.
• Debug complex issues at the research/infrastructure seam that appear at scale.
• Partner with adjacent RL teams to advance the overall RL stack.

What you'll need

• Strong empirical research skills in reinforcement learning or a closely adjacent area.
• Ability to own large experiments end-to-end, from design through interpretation.
• Proficiency in Python.
• Experience working with large-scale or distributed ML systems.
• Comfort operating at the research/systems boundary, including debugging.
• Care about societal impacts of AI and responsible scaling.

Details

• Location-based hybrid policy: at least 25% time in an office.