RL Systems Engineer: Scale & Research

Anthropic Limited; San Francisco (CA); On-site; USD 500,000 - 850,000; Full time

Job summary

Anthropic is seeking a Research Engineer to build and own the RL training system that underpins our production and research runs in SF. You will collaborate with research teams, implement new training methods, and optimize performance across orchestration, environments, training, and inference.

The role requires deep Python ML experience, experience with large-scale RL or similar systems, and fluency in modern ML frameworks.

Qualifications

• Proficiency in Python and experience working in, debugging, and improving a large ML codebase.
• Experience with large-scale machine learning training (reinforcement learning, pretraining, or post-training) or the systems that support it.
• Experience with at least one modern ML framework (JAX, PyTorch, or similar).
• Ability to design controlled experiments and reach conclusions you and others can trust.
• Ability to balance research exploration with engineering implementation.
• Strong written and verbal communication skills.
• Care about the societal impacts of your work and are committed to developing safe and beneficial systems.

Responsibilities

• Build, own, and improve the core RL training system that serves Anthropic's production and research runs
• Work across the stack (orchestration, environments, training, inference, evaluation) wherever the system needs it
• Study how RL training behaves at scale and contribute to the research that improves it, in collaboration with teams across Anthropic
• Implement new training methods as stable, fast, well-tested code
• Improve the speed and efficiency of RL training and evaluation through profiling, optimization, and benchmarking
• Make the system easier for researchers to build on, through clean abstractions, clear APIs, and automated testing
• Debug hard problems across the stack, from a run that has quietly drifted to a distributed systems failure that only shows up at scale
• Communicate results clearly, in writing and in discussion

Skills

Python

ML codebase

Large-scale ML training

ML frameworks (JAX, PyTorch)

Experiment design

Research/Engineering balance

Communication

Societal impact awareness

Education

Bachelor's degree

Job description

Anthropic is seeking a Research Engineer to build and own the RL training system that underpins our production and research runs in SF. You will collaborate with research teams, implement new training methods, and optimize performance across orchestration, environments, training, and inference.

The role requires deep Python ML experience, experience with large-scale RL or similar systems, and fluency in modern ML frameworks.