Research Engineer: Large-Scale RL & Production Recipes

Mat Vin; Greater London; Hybrid; GBP 106,000 - 144,000; Full time

Benefits offered by this job

Competitive compensation

Equity option

Generous vacation and parental leave

Flexible working hours

Office space in SF

Job summary

Anthropic is seeking a Research Engineer for the RL Scaling Science team to design and run large-scale reinforcement learning experiments and ship validated findings into production training. This role sits at the research/engineering boundary, requiring rigorous experimentation, benchmarks, and collaboration with adjacent RL teams to advance our scalable AI systems.

You will work with Python on frontier-scale training, translating insights into practical training recipes while considering

Qualifications

• Strong empirical research skills in Reinforcement Learning or related ML areas.
• Experience designing and running large-scale experiments.
• Ability to translate research findings into production training recipes.
• Proven capability to own end-to-end experiments from design to interpretation.

Responsibilities

• Design, run, and interpret large-scale RL experiments, with rigorous analysis.
• Investigate RL behavior as horizon, compute, and model size increase.
• Build benchmarks for long-horizon RL to ensure measurable progress.
• Translate validated findings into production training recipes.
• Debug complex issues at the research/systems boundary and scale.
• Collaborate with adjacent RL teams to advance the RL stack.

Skills

Python

Large-scale ML training

Reinforcement Learning

Experiment design

Productionization

Education

Bachelor’s degree or equivalent (relevant field)

Tools

Distributed ML systems

Job description

Anthropic is seeking a Research Engineer for the RL Scaling Science team to design and run large-scale reinforcement learning experiments and ship validated findings into production training. This role sits at the research/engineering boundary, requiring rigorous experimentation, benchmarks, and collaboration with adjacent RL teams to advance our scalable AI systems.

You will work with Python on frontier-scale training, translating insights into practical training recipes while considering