Research Engineer - Reinforcement Learning (Remote)

About the Role

We are seeking a Research Engineer - Reinforcement Learning to join our team at Anthropic. This Research Engineer remote position offers an exciting opportunity to work on cutting-edge AI systems that prioritize safety and reliability. As part of our rapidly growing team, you will collaborate with researchers and engineers to enhance the capabilities and safety of large language models.

What You'll Do

• Collaborate with a diverse group of researchers and engineers to advance reinforcement learning methodologies.
• Implement novel approaches in reinforcement learning, focusing on creating agentic models for open-ended tasks.
• Architect and optimize core reinforcement learning infrastructure, enhancing our systems for complex research workflows.
• Design, implement, and test novel training environments and methodologies for reinforcement learning agents.
• Drive performance improvements through profiling, optimization, and benchmarking of our systems.
• Implement efficient caching solutions and debug distributed systems to accelerate training and evaluation workflows.
• Work closely with research and engineering teams to develop automated testing frameworks and scalable infrastructure.

Requirements

• Proficiency in Python and async/concurrent programming with frameworks like Trio.
• Experience with machine learning frameworks such as PyTorch, TensorFlow, or JAX.
• Industry experience in machine learning research.
• Strong systems design and communication skills.
• Passion for AI and commitment to developing safe and beneficial systems.

Nice to Have

• Familiarity with LLM architectures and training methodologies.
• Experience with reinforcement learning techniques and environments.
• Knowledge of Kubernetes and distributed systems.
• Experience with Rust and/or C++.

What We Offer

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.
• Relocation package for eligible candidates.

Join us as a Research Engineer - Reinforcement Learning remote and contribute to our mission of building safe and beneficial AI systems. We encourage you to apply even if you do not meet every qualification, as we value diverse perspectives and experiences.