Red Team Engineer, Safeguards

Overview

Red Team Engineer, Safeguards to help uncover vulnerabilities and novel abuse paths across Anthropic’s deployed AI systems and product surfaces.

What you'll do

• Conduct comprehensive adversarial testing across product surfaces.
• Develop creative attack scenarios that combine multiple exploitation techniques.
• Research and implement novel testing approaches for emerging AI capabilities.
• Design and execute “full kill chain” attacks to emulate real-world threat actors.
• Build and maintain systematic testing methodologies across every aspect of systems.
• Develop automated testing frameworks for continuous assessment at scale.
• Collaborate with Product, Engineering, and Policy to translate findings into improvements.

What you'll need

• Experience in penetration testing, red teaming, or application security.
• Experience in model jailbreaking and testing large-scale agentic workflows.
• Strong web application security skills and hands-on use of tools like Burp Suite and Metasploit.
• Experience building custom automation, including LLM-specific testing frameworks.
• A track record of discovering novel attack vectors and chaining vulnerabilities.
• A public record such as CVEs, blog posts, or disclosed bug bounty reports.
• Strong written and verbal communication skills to explain technical concepts.

Details

• Annual compensation range is listed as $320,000–$405,000 USD.
• Location-based hybrid policy: being in an office at least 25% of the time.
• Visa sponsorship is available for some roles/candidates.
• Minimum education: Bachelor’s degree or equivalent combination of education, training, and/or experience.