Red Team Engineer, Safeguards

ABOUT THE ROLE Anthropic is a rapidly growing organization dedicated to creating reliable, interpretable, and steerable AI systems. Our mission is to ensure AI is safe and beneficial for users and society as a whole. We're seeking a Red Team Engineer to join our Safeguards team, where you'll play a critical role in ensuring the safety of our deployed AI systems and products. WHAT YOU'LL DO As a Red Team Engineer, you'll take an adversarial approach to uncover vulnerabilities across our product ecosystem, simulating sophisticated threat actors who chain multiple attack vectors to achieve their objectives. Your work will span from technical infrastructure vulnerabilities to emergent risks from advanced AI capabilities. You'll investigate the full spectrum of potential abuse, from coordinated account manipulation and payment fraud to novel exploitation of product features. Key responsibilities will include: Conducting comprehensive adversarial testing across Anthropic's product surfaces, developing creative attack scenarios that combine multiple exploitation techniques Researching and implementing novel testing approaches for emerging capabilities, including agent systems, tool use, and new interaction paradigms Designing and executing "full kill chain" attacks that emulate real-world threat actors attempting to achieve specific malicious objectives Building and maintaining systematic testing methodologies that evaluate every aspect of our systems Developing automated testing frameworks to enable continuous assessment at scale Collaborating with Product, Engineering, and Policy teams to translate findings into concrete improvements Helping establish metrics for measuring detection effectiveness of novel abuse WHAT YOU'LL NEED To be successful in this role, you'll need: Experience in penetration testing, red teaming, or application security Experience in model jailbreaking and testing large-scale agentic workflows for non-obvious prompt injection vectors Strong technical skills in web application security, including hands-on expertise with security testing tools (e.g., Burp Suite, Metasploit, custom scripting frameworks) Experience building custom automation, including LLM-specific testing frameworks A track record of discovering novel attack vectors and chaining vulnerabilities in creative ways A public body of work such as CVEs, blog posts, or disclosed bug bounty reports Strong written and verbal communication skills, with the ability to explain technical concepts to varied audiences WHY REMOTE Anthropic offers a hybrid work model, with the expectation that staff will be in one of our offices at least 25% of the time. However, some roles may require more time in our offices. We also sponsor visas for eligible candidates. BENEFITS The annual compensation range for this role is $320,000 - $405,000 USD. We offer a comprehensive benefits package, including a minimum education requirement of a Bachelor's degree or equivalent combination of education, training, and/or experience, and a minimum years of experience requirement that will correlate with the internal job level requirements for the position.