Research Engineer, RL Scaling Science

Anthropic's mission is to create reliable, interpretable, and steerable AI systems.

As a Research Engineer on the RL Scaling Science team, you'll design and run large-scale experiments to understand and resolve bottlenecks, build benchmarks for long-horizon progress, and ship validated findings into production training.

Key Responsibilities

• Design, run, and interpret large-scale RL experiments
• Investigate how RL improves with horizon, compute, and model size growth
• Build and maintain benchmarks for long-horizon RL
• Translate validated findings into production training recipes
• Debug complex issues at the research-infrastructure boundary
• Partner with adjacent RL teams to advance the RL stack

Minimum Qualifications

• Strong empirical research skills in Reinforcement Learning or related areas
• Ability to own large experiments end-to-end
• Proficiency in Python and experience with large-scale ML systems
• Comfort operating at the research-systems boundary
• Care about AI's societal impacts and responsible scaling

Preferred Qualifications

• Published or shipped work in long-horizon RL or RL fundamentals
• Experience translating research findings into production training recipes
• Demonstrated large-scale industry impact via RL interventions
• Experience with frontier-scale training runs

Logistics

• Annual Salary: £375,000-£640,000 GBP
• Location-based hybrid policy: 25% office time
• Visa sponsorship available