Anthropic AI Security Fellow

<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><p><strong><em>Please apply by January 12, 2026 <a href="https://constellation.fillout.com/anthropicsecurityfellows">using this link</a></em></strong></p> <h1><span style="font-size: 18pt;"><strong>AI Security at Anthropic</strong></span></h1> <p>We believe we are at an inflection point for AI’s impact on cybersecurity. Models are now useful for cybersecurity tasks in practice: for example, Claude can now <a href="https://red.anthropic.com/2025/cyber-competitions/">outperform human teams</a> in some cybersecurity competitions and help us discover <a href="https://claude.com/blog/automate-security-reviews-with-claude-code">vulnerabilities in our own code</a>.&nbsp;</p> <p>We are looking for researchers and engineers to help us accelerate defensive use of AI to secure code and infrastructure.&nbsp;</p> <h1><span style="font-size: 18pt;"><strong>Anthropic Fellows Program Overview</strong></span></h1> <p>The Anthropic Fellows Program is designed to accelerate AI security and safety research, and foster research talent. We provide funding and mentorship to promising technical talent - regardless of previous experience - to research the frontier of AI security and safety for four months.</p> <p>Fellows will primarily use external infrastructure (e.g. open-source models, public APIs) to work on an empirical project aligned with our research priorities, with the goal of producing a <strong>public output</strong> (e.g. a paper submission). In our previous cohorts, over 80% of fellows produced papers (more below).&nbsp;</p> <p>We run multiple cohorts of Fellows each year. This application is for our next two cohorts, starting in May and July 2026.</p> <h1><span style="font-size: 18pt;"><strong>What to Expect</strong></span></h1> <ul> <li>Direct mentorship from Anthropic researchers&nbsp;</li> <li>Access to a shared workspace (in either Berkeley, California or London, UK)</li> <li>Connection to the broader AI safety research community</li> <li>Weekly stipend of 3,850 USD / 2,310 GBP / 4,300 CAD &amp; access to benefits (benefits vary by country)</li> <li>Funding for compute (~$15k/month) and other research expenses</li> </ul> <h1><span style="font-size: 18pt;"><strong>Mentors, Research Areas, &amp; Past Projects</strong></span></h1> <p>Fellows will undergo a project selection &amp; mentor matching process. Potential mentors include:</p> <ul> <li>Nicholas Carlini</li> <li>Keri Warr</li> <li>Evyatar Ben Asher</li> <li>Keane Lucas</li> <li>Newton Cheng</li> </ul> <p>On our <a href="https://alignment.anthropic.com/">Alignment Science</a> and <a href="https://red.anthropic.com/">Frontier Red Team</a> blogs, you can read about some past Fellows projects, including:</p> <ul> <li><a href="https://red.anthropic.com/2025/smart-contracts/">AI agents find $4.6M in blockchain smart contract exploits:</a>&nbsp;Winnie Xiao and Cole Killian, mentored by Nicholas Carlini and Alwin Peng</li> <li><a href="https://alignment.anthropic.com/2025/strengthening-red-teams/">Strengthening Red Teams: A Modular Scaffold for Control Evaluations:</a>&nbsp;Chloe Loughridge et al., mentored by Jon Kutasov and Joe Benton</li> </ul> <h1><span style="font-size: 18pt;"><strong>You may be a good fit if you</strong></span></h1> <ul> <li>Are motivated by reducing catastrophic risks from advanced AI systems</li> <li>Are excited to transition into full-time empirical AI safety research and would be interested in a full-time role at Anthropic</li> </ul> <p style="padding-left: 80px;"><strong>Please note:</strong> We do not guarantee that we will make any full-time offers to fellows. H ... (truncated, view full listing at source)