Research Engineer, RL Scaling Science

ABOUT THE ROLE Anthropic's Research Engineer, RL Scaling Science, plays a crucial role in advancing the company's mission to create reliable, interpretable, and steerable AI systems. As a member of the RL Scaling Science team, you will contribute to the development of beneficial AI systems by studying the behavior of reinforcement learning as it scales and turning that understanding into training recipes for frontier models. WHAT YOU'LL DO As a Research Engineer, you will 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 recipes. You will work at the boundary between research and engineering, where the path from a robust result to production is short. Your responsibilities will include: - Designing, running, and interpreting large-scale RL experiments - Investigating how RL improves as horizon, compute, and model size grow - Building and maintaining benchmarks for long-horizon RL - Translating validated findings into production training recipes - Debugging complex issues at the seam where research meets infrastructure - Partnering closely with adjacent RL teams across research and engineering WHAT YOU'LL NEED To be successful in this role, you will need strong empirical research skills in Reinforcement Learning, large-scale ML training, or a closely adjacent area. You should be able to own large experiments end-to-end, from design through interpretation, and have proficiency in Python and experience working with large-scale or distributed ML systems. You should also be comfortable operating at the research/systems boundary and have a demonstrated ability to debug complex issues. WHY REMOTE Anthropic is a remote-friendly company, and this role will be performed remotely. As a Research Engineer, you will have the flexibility to work from anywhere and collaborate with the team through digital channels. BENEFITS Anthropic offers a competitive annual salary range of £375,000 - £640,000 GBP, as well as a range of benefits, including a health plan, parental leave, and education stipend. The company also offers visa sponsorship and a flexible schedule, allowing you to balance your work and personal life.