RL Systems Engineer: Scale Training & Research

Anthropic Limited; Seattle (WA); Hybrid; USD 500,000 - 850,000; Full time

Job summary

Anthropic in Seattle is seeking a Research Engineer to own and advance the core RL training system used by production and research. You will work across orchestration, environments, training, inference, and evaluation to understand and improve RL at scale.

You will implement new training methods, profile and optimize workloads, and help researchers build on a robust framework. Strong Python, ML experience, and clear communication are essential, as is a commitment to safe, beneficial AI.

Qualifications

• Proficiency in Python and large ML codebases.
• Experience with large-scale ML training (reinforcement learning) or related systems.
• Experience with a modern ML framework (e.g., JAX, PyTorch).
• Ability to design controlled experiments and draw trustworthy conclusions.
• Balance between research exploration and engineering implementation.
• Strong written and verbal communication skills.
• Commitment to safe and beneficial AI.

Responsibilities

• Own and improve the RL training system used across production and research.
• Collaborate across orchestration, environments, training, inference, and evaluation.
• Study RL training at scale and contribute to related research.
• Implement new training methods as robust, fast, and well-tested code.
• Improve RL training efficiency via profiling, optimization, and benchmarking.
• Make the system approachable for researchers with clean APIs and tests.
• Debug complex issues from drifted runs to distributed-systems failures.
• Communicate results clearly in writing and discussion.

Skills

Python proficiency

Large-scale ML training

ML framework (JAX, PyTorch)

Experimental design

Engineering + research balance

Clear written/verbal communication

Societal impact focus

Education

Bachelor’s degree

Job description

Anthropic in Seattle is seeking a Research Engineer to own and advance the core RL training system used by production and research. You will work across orchestration, environments, training, inference, and evaluation to understand and improve RL at scale.

You will implement new training methods, profile and optimize workloads, and help researchers build on a robust framework. Strong Python, ML experience, and clear communication are essential, as is a commitment to safe, beneficial AI.