Research Engineer, Cybersecurity

<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>The Security team protects Anthropic's AI systems and maintains the trust of our users and society. As a Research Engineer on the team, you'll help safely advance the capabilities of our models in secure coding, vulnerability remediation, and other areas of defensive cybersecurity.</p> <p>This role blends research and engineering. You'll develop new approaches and build them in code. Your work will include designing and implementing RL environments, running experiments and evaluations, delivering your work into production training runs, and working with researchers, engineers, and cybersecurity specialists both inside and outside Anthropic.</p> <p>The role asks for domain expertise in cybersecurity paired with interest or experience in training safe AI models. You might be a security researcher curious about how LLMs could change your work, a security engineer interested in how AI could help harden systems at scale, or a detection and response professional wondering how models could improve defensive workflows.</p> <h2>Key responsibilities</h2> <ul> <li>Design, build, and maintain RL environments and evaluations that measure and improve model capabilities in secure coding, vulnerability discovery and remediation, and other defensive security tasks</li> <li>Run experiments to develop and test new training approaches, and deliver successful results into production training runs</li> <li>Partner with researchers, engineers, and security specialists across Anthropic to understand where AI can strengthen defensive workflows, and build toward those n