Research Engineer – RL Scaling Science

About the role

Anthropic’s RL Scaling Science team studies how reinforcement learning behaves as we scale it across model size, compute, and task horizon. As a Research Engineer you will design and run large‑scale experiments, build benchmarks for long‑horizon RL, and translate validated findings into production training recipes.

Key responsibilities

• Design, run, and interpret large‑scale RL experiments, rigorously reasoning about data.
• Investigate RL performance as horizon, compute, and model size grow.
• Build and maintain benchmarks for long‑horizon RL to ensure measurable, reproducible progress.
• Translate validated findings into production training recipes, judging robustness.
• Debug complex issues at the research‑infrastructure seam that appear only at scale.
• Partner with adjacent RL teams across research and engineering to advance the RL stack.

Required profile

• Strong empirical research skills in Reinforcement Learning, large‑scale ML training, or a closely adjacent area.
• Proven ability to own large experiments end‑to‑end, from design through interpretation.
• Proficiency in Python and experience with large‑scale or distributed ML systems.
• Comfort operating at the research/systems boundary, including debugging where the two meet.
• Commitment to the societal impacts of AI and responsible scaling.

Required skills

• Python programming
• Large‑scale distributed machine‑learning systems
• Reinforcement Learning