<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>Our team builds, tests, deploys, and monitors the classifiers that block internal agents from taking dangerous actions. These classifiers run across RL, evals, and internal deployments, and are designed to catch things like sandbox escape attempts or exfiltration of sensitive data.</p>
<p>When a classifier flags an action, it can <a href="https://www.anthropic.com/news/improving-alignment-security-efforts" target="_blank">block the action before the tool call runs, end the task, and alert a human</a>. This is one layer of a defence-in-depth with several layers that reinforce each other: what our classifiers flag feeds into offline monitoring, and the findings from that go back into better classifiers and safer environment design.</p>
<p>The work combines research and production engineering:</p>
<ul>
<li>
<p>The research problem is building high recall and high precision classifiers to catch rare, novel, and sometimes adversarial behaviour. There are also several narrow research questions to answer - for example, how to deplo