Red Team Engineer, Safeguards

📋 Description

• Conduct adversarial testing across Anthropic's product surfaces
• Research and implement novel testing approaches for emergent capabilities
• Design and execute "full kill chain" attacks simulating real-world threat actors
• Build and maintain systematic testing methodologies across our systems
• Develop automated testing frameworks for continuous, scalable assessment
• Collaborate with Product, Engineering, and Policy to translate findings into improvements

🎯 Requirements

• Penetration testing, red teaming, or application security experience
• Model jailbreaking and testing large-scale agentic workflows for prompt injection
• Web app security expertise with tools (Burp Suite, Metasploit, scripting)
• Experience building custom automation, including LLM testing frameworks
• Track record of discovering novel attack vectors and chaining vulnerabilities
• Strong written and verbal communication; explain technical concepts clearly

🎁 Benefits

• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space for collaboration