RL Research Engineer — Scalable, Safe AI Systems

Anthropic Limited; San Francisco (CA); Híbrido; USD 500.000 - 850.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity donation matching

Generous vacation & parental leave

Flexible working hours

Office in SF

Descripción de la vacante

Anthropic is seeking a Research Engineer in Reinforcement Learning to advance capabilities and safety of large language models. You will blend research and engineering, implement novel approaches, and contribute to research directions.

Expect to work on agentic models via tool use for open-ended tasks such as computer use and autonomous software generation. You will architect core RL infrastructure, design new training environments, and drive performance improvements across the stack.

Formación

• Bachelor’s degree in a field relevant to the role.
• Strong programming ability in Python with modern ML tooling.
• Experience delivering ML research in production or deployment contexts.
• Experience balancing exploratory research with engineering implementation.

Responsabilidades

• Architect and optimize reinforcement learning infrastructure and experiment management across GPU clusters.
• Design and test training environments and evaluation methodologies for RL agents.
• Improve system performance via profiling, optimization, and distributed debugging.
• Collaborate across research and engineering to build scalable AI research infrastructure.

Conocimientos

Python

Async/Concurrent

ML frameworks

Research–to–engineering

Pair programming

Code quality

System design

Communication

Educación

Bachelor’s degree in a relevant field

Herramientas

Kubernetes

Virtualization

Sandboxed execution environments

Distributed systems

Rust/C++

Descripción del empleo

Anthropic is seeking a Research Engineer in Reinforcement Learning to advance capabilities and safety of large language models. You will blend research and engineering, implement novel approaches, and contribute to research directions.

Expect to work on agentic models via tool use for open-ended tasks such as computer use and autonomous software generation. You will architect core RL infrastructure, design new training environments, and drive performance improvements across the stack.