Hybrid RL Systems Engineer — Scale Training & Research

Anthropic Limited; New York (NY); Hybride; USD 500 000 - 850 000; Plein temps

Avantages offerts par ce poste

Competitive compensation

Equity donation matching

Generous vacation and parental leave

Flexible working hours

Office in San Francisco

Résumé du poste

Anthropic is seeking a Research Engineer to join the RL training team, building and owning the RL training system that serves production and research runs. You will work across the stack to deploy models and run experiments with researchers.

You will contribute to scalable RL research and collaborate with multiple teams to improve training methods, profiling, and benchmarking, while ensuring robust, well-tested code and clear communication.

Qualifications

• Proficiency in Python and debugging a large ML codebase.
• Experience with large-scale ML 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.

Responsabilités

• 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.

Connaissances

Python

ML training

ML frameworks

Experiment design

Communication

Ethical AI

Formation

Bachelor’s degree

Outils

Rust

C++

Description du poste

Anthropic is seeking a Research Engineer to join the RL training team, building and owning the RL training system that serves production and research runs. You will work across the stack to deploy models and run experiments with researchers.

You will contribute to scalable RL research and collaborate with multiple teams to improve training methods, profiling, and benchmarking, while ensuring robust, well-tested code and clear communication.