Red Team Engineer, Safeguards

Responsibilities

• Conduct comprehensive adversarial testing across Anthropic's product surfaces to develop creative attack scenarios.
• Research and implement novel testing approaches for emerging capabilities like agent systems and tool use.
• Design and execute "full kill chain" attacks that emulate real-world threat actors.
• Build and maintain systematic testing methodologies and automated frameworks for continuous assessment at scale.
• Collaborate with Product, Engineering, and Policy teams to translate security findings into concrete product improvements.
• Help establish metrics for measuring the detection effectiveness of novel abuse patterns.

Requirements

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

Preferred Qualifications

• Experience with AI/ML security or adversarial machine learning.
• Understanding of AI safety considerations and modern guardrails against jailbreaks.
• Experience testing API security, rate-limiting systems, and business logic vulnerabilities.
• Background in anti-fraud, trust & safety, or abuse prevention systems.
• Familiarity with distributed systems and infrastructure security.

Benefits

• Competitive annual salary range ($320,000 - $405,000 USD).
• Generous vacation and parental leave.
• Flexible working hours.
• Optional equity donation matching.

About the Company

Anthropic is a public benefit corporation dedicated to creating reliable, interpretable, and steerable AI systems. Our mission is to ensure that AI is safe and beneficial for users and society as a whole. We operate as a highly collaborative team of researchers, engineers, and policy experts working on large-scale research efforts to advance trustworthy AI.