Research Engineer, Reinforcement Learning

Job title: Research Engineer, Reinforcement Learning

About the Role As a Research Engineer within Reinforcement Learning, you will collaborate with a diverse group of researchers and engineers to advance the capabilities and safety of large language models. This role blends research and engineering responsibilities, requiring you to both implement novel approaches and contribute to the research direction.

What You'll Do

• Architect and optimize core reinforcement learning infrastructure, from clean training abstractions to distributed experiment management across GPU clusters.
• Help scale our systems to handle increasingly complex research workflows.
• Design, implement, and test novel training environments, evaluations, and methodologies for reinforcement learning agents which push the state of the art for the next generation of models.
• Drive performance improvements across our stack through profiling, optimization, and benchmarking.
• Implement efficient caching solutions and debug distributed systems to accelerate both training and evaluation workflows.
• Collaborate across research and engineering teams to develop automated testing frameworks, design clean APIs, and build scalable infrastructure that accelerates AI research.

What We're Looking For

• Proficient in Python and async/concurrent programming with frameworks like Trio.
• Experience with machine learning frameworks (PyTorch, TensorFlow, JAX).
• Industry experience in machine learning research.
• Ability to balance research exploration with engineering implementation.
• Enjoy pair programming and care about code quality, testing, and performance.
• Strong systems design and communication skills.
• Passion for AI and commitment to safe, beneficial systems.
• Strong candidates may have: familiarity with LLM architectures and training methodologies; experience with reinforcement learning techniques and environments; virtualization and sandboxed code execution environments; Kubernetes; distributed systems or high-performance computing; Rust and/or C++.

Nice to Have

• Familiarity with LLM architectures and training methodologies.
• Experience with reinforcement learning techniques and environments.
• Experience with virtualization and sandboxed code execution environments.
• Experience with Kubernetes and distributed systems or HPC.
• Proficiency with Rust and/or C++.

Compensation & Benefits

• Annual Salary: £260,000 - £630,000 GBP
• Salary currency noted for compensation: USD in application system.
• We sponsor visas where possible and support immigration processes; rolling applications.