Summary

Research engineer role in anthropic’s reinforcement learning team, working on agentic models via tool use, reinforcement learning infrastructure, training environments, evaluations, and performance improvements for large language models. The role blends research and engineering, including distributed experiment management across gpu clusters and building scalable infrastructure for training and evaluation. Hybrid policy expects staff in an office at least 25% of the time.

Responsibilities

• Architect and optimize reinforcement learning infrastructure
• Design and test training environments and evaluations
• Improve performance via profiling and optimization
• Implement caching solutions and debug distributed systems
• Build automated testing frameworks and clean apis
• Develop scalable infrastructure for ai research