Research Engineer (RL Scaling Science)

Location: Hybrid: Must be based in London, UK (minimum 25% office presence)

Salary: £375,000 - £640,000 GBP

Company

Anthropic is a public benefit corporation dedicated to creating reliable, interpretable, and steerable AI systems that are safe and beneficial for society.

What you will do

• Design, run, and interpret large-scale RL experiments to understand scaling behavior across model size and compute.
• Build and maintain benchmarks for long-horizon RL to ensure progress is measurable and reproducible.
• Translate validated research findings into production training recipes for frontier models.
• Debug complex failures occurring at the seam where research meets large-scale infrastructure.
• Collaborate with adjacent RL teams to advance the overall RL stack and capabilities.

Requirements

• Strong empirical research skills in Reinforcement Learning or large-scale ML training.
• Ability to own large experiments end-to-end, from design through interpretation.
• Proficiency in Python and experience with distributed ML systems.
• Comfort operating and debugging at the research/systems boundary.
• Bachelor's degree or equivalent combination of education and professional experience.

Nice to have

• 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 working on frontier-scale training runs with long trajectories.

Culture & Benefits

• Collaborative "big science" environment focusing on high-impact research over small puzzles.
• Competitive compensation with optional equity donation matching.
• Generous vacation and parental leave policies.
• Flexible working hours and high-quality collaborative office space.
• Visa sponsorship available for eligible candidates.