Reinforcement Learning Research Engineer — Scale AI Systems

anthropic; Greater London; Híbrido; GBP 260.000 - 630.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity donation matching (optional)

Generous vacation and parental leave

Flexible working hours

Office space

Descripción de la vacante

Anthropic is seeking a Research Engineer in Reinforcement Learning to collaborate with researchers and engineers to advance capabilities and safety of large language models. The role blends research and engineering, implementing novel approaches and shaping research directions, including agentic models via tool use for open-ended tasks and improving reasoning in mathematics.

You will architect RL infrastructure, design training environments, and accelerate AI research with scalable systems and

Formación

• Proficiency in Python and async/concurrent programming.
• Experience with ML frameworks (PyTorch, TensorFlow, JAX).
• Industry experience in ML research.
• Ability to balance research exploration with engineering implementation.
• Enjoy pair programming and writing clean code.
• Strong systems design and communication skills.
• Passionate about safe and beneficial AI.

Responsabilidades

• Architect and optimize core reinforcement learning infrastructure and experiment management across GPU clusters.
• Design, implement, and test training environments and evaluation methodologies for RL agents.
• Drive performance improvements through profiling, optimization, and distributed systems debugging.
• Collaborate with research and engineering teams to build scalable AI infrastructure and testing frameworks.

Conocimientos

Python

Async programming (Trio)

ML frameworks (PyTorch, TensorFlow, JX

Research experience

Pair programming

Systems design

Communication skills

Educación

Bachelor's degree

Herramientas

None

Descripción del empleo

Anthropic is seeking a Research Engineer in Reinforcement Learning to collaborate with researchers and engineers to advance capabilities and safety of large language models. The role blends research and engineering, implementing novel approaches and shaping research directions, including agentic models via tool use for open-ended tasks and improving reasoning in mathematics.

You will architect RL infrastructure, design training environments, and accelerate AI research with scalable systems and