Staff Red Team Engineer, Safeguards

📋 Description

• Conduct adversarial testing across Anthropic’s product surfaces
• Research and implement novel testing for emergent AI capabilities
• Design and execute full kill chain attacks emulating real attackers
• Build and maintain systematic testing methodologies across systems
• Develop automated testing frameworks for scale and speed
• Collaborate with Product, Engineering, and Policy teams to apply findings

🎯 Requirements

• Demonstrated experience in penetration testing, red teaming, or app security
• Strong web app security skills with Burp Suite, Metasploit, or scripting
• Track record of novel attack vectors and vulnerability chaining
• Public CVEs, blog posts, or bug bounty reports
• Experience with security testing tools and custom automation
• Strong written and verbal communication skills

🎁 Benefits

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