Software Engineer, Safeguards Evals

<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 class="heading">About the role</h2> <p>How do we know our safety systems actually catch misuse? Anthropic increasingly uses AI to investigate potential misuse of Claude — analyzing real-world traffic to surface bad actors, policy violations, and emerging threats. Its findings inform enforcement actions and model launch decisions, which means we need rigorous, trustworthy answers to questions like: Does the monitoring agent catch what it should? Where does it fail? Does it stay reliable as adversaries adapt, as models improve, and as the agent itself changes?</p> <p>This role builds the evaluation infrastructure that answers those questions. You'll sit at the intersection of applied ML research and engineering — designing experiments to measure how well an investigative agent performs across harm areas, building datasets that represent real abuse rather than synthetic benchmarks, and shipping those methods into pipelines that gate every change to the system. Your work directly determines how much trust Anthropic can place in its automated abuse detection, and where we invest to make it better.</p> <h2 class="heading">Key responsibilities</h2> <ul> <li> <p>Build and own the evaluation harness for an agentic investigation system — defining metrics, test cases and grading approaches for a complex long horizon agent</p> </li> <li> <p>Construct high-quality eval datasets representing real-world misuse across harm areas (e.g., cyber attacks, bio weapons, influence operations), drawing from real traffic patterns and synthetic generation</p> </li> <li> <p>Measure agent perfor