Research Engineer, RL Scaling Science

• Join Anthropic's RL Scaling Science team studying how reinforcement learning behaves as it scales across model size, compute, and task horizon. • Turn that understanding into the training recipes behind Anthropic's frontier models. • Work at the boundary between research and engineering, where problems are open, experiments run at frontier scale, and the path from a robust result to production is short. • Be based in London with a hybrid policy expecting at least 25% of time in the office.

• Bring strong empirical research skills in Reinforcement Learning, large-scale ML training, or a closely adjacent area. • Demonstrate the ability to own large experiments end-to-end, from design through interpretation. • Be proficient in Python with experience working with large-scale or distributed ML systems. • Be comfortable operating at the research/systems boundary, including debugging where the two meet. • Care about the societal impacts of AI and responsible scaling.

• Have published or shipped work in long-horizon RL or RL fundamentals. • Have experience translating research findings into production training recipes. • Have demonstrated large-scale industry impact via RL interventions. • Have experience working on frontier-scale training runs with long trajectories.

• Design, run, and interpret large-scale RL experiments, reasoning rigorously about what the data does and doesn't show. • Investigate how RL improves as horizon, compute, and model size grow. • Build and maintain benchmarks for long-horizon RL so progress is measurable and reproducible. • Translate validated findings into production training recipes, exercising judgement about when a result is robust enough to ship. • Debug complex issues at the seam where research meets infrastructure — failures that only appear at scale. • Partner closely with adjacent RL teams across research and engineering and advance the overall RL stack.

• Receive competitive compensation between £375,000 and £640,000 GBP annually. • Get visa sponsorship where possible — Anthropic retains an immigration lawyer to support this. • Take generous parental leave. • Enjoy generous vacation and flexible working hours. • Optional equity donation matching. • Work alongside world-class researchers and engineers on frontier-scale training runs.

Anthropic's mission is to create reliable, interpretable, and steerable AI systems. They want AI to be safe and beneficial for users and society as a whole. The team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. Anthropic is a public benefit corporation offering competitive compensation and benefits.