Staff+ Research Scientist, Multi-Agent

<div class="content-intro"><h2><strong>About Anthropic</strong></h2> <p>Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.</p></div><h2>About the role:</h2> <p>Multi-Agent systems are becoming an increasingly important part of how AI is deployed, whether via fast small-model subagents inside a product, or <a href="https://bun.com/blog/bun-in-rust">large groups of agents</a> solving <a href="https://www.anthropic.com/research/formalizing-fermats-last-theorem">very large problems</a>. Training Claude to be maximally effective and safe within large groups is a challenging new area of reinforcement learning, and represents a new axis for scaling test time compute.</p> <p>We are looking for researchers who have experience training multi-agent systems at the largest scale and an appreciation for the incentives and mechanism design that come into play.</p> <h2>Responsibilities:</h2> <ul> <li>Help create and optimize environments and data for model training that maximize Claude’s performance or ease of use on agentic tasks</li> <li>Ideate, develop, and compare the performance of different agent harness configurations (eg memory, context management, communication architectures for agents)</li> <li>Design and implement rigorous quantitative benchmarks for large scale agentic tasks</li> <li>Work with our product org to find solutions to our most vexing challenges in applying agents to our products</li> </ul> <p><br><br></p> <h2>You may be a good fit if you:</h2> <ul> <li>Have experience with large-scale RL on language models</li> <li>Have experience training multi-agent systems</li> <li>Enjoy going deeply into the roots of a problem and understanding its foundations, rather than its surface.</li> <li>Have good