Red Team Engineer (AI Safeguards)

Location: Remote-Friendly (Travel Required) | San Francisco, CA

Salary: $320,000–$405,000 USD (annual)

Company

Anthropic builds reliable, interpretable, and steerable AI systems with a focus on safety and beneficial outcomes.

What you will do

• Run comprehensive adversarial testing across product surfaces, creating creative multi-technique attack scenarios.
• Research and implement novel testing approaches for emerging AI capabilities (agent systems, tool use, and new interaction paradigms).
• Design and execute full kill-chain attacks that emulate real-world threat actors pursuing specific malicious objectives.
• Build and maintain systematic testing methodologies covering every aspect of systems, including continuous assessment at scale via automated testing frameworks.
• Collaborate with Product, Engineering, and Policy teams to turn findings into concrete improvements and define metrics for detection effectiveness.

Requirements

• Experience in penetration testing, red teaming, or application security.
• Experience with model jailbreaking and testing large-scale agentic workflows for non-obvious prompt injection vectors.
• Strong web application security skills with hands-on security testing tools (e.g., Burp Suite, Metasploit, custom scripting frameworks).
• Experience building custom automation, including LLM-specific testing frameworks.
• Proven track record of discovering novel attack vectors and chaining vulnerabilities creatively (e.g., CVEs, blog posts, or disclosed bug bounty reports).
• Strong written and verbal communication skills to explain technical concepts to varied audiences.

Nice to have

• Experience with AI/ML security or adversarial machine learning.
• Understanding of AI safety beyond traditional security, including modern guardrails against jailbreaks.
• Experience testing API security and rate-limiting systems.
• Background in anti-fraud, trust & safety, or abuse prevention systems; authorization bypass and business logic vulnerabilities.
• Familiarity with distributed systems, infrastructure security, and abuse detection mechanisms (including engineering novel bypasses).

Culture & Benefits

• Location-based hybrid policy: expect to be in one of the offices at least 25% of the time (some roles may require more).
• Visa sponsorship available; reasonable efforts made to support offers where possible.
• Competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, and flexible working hours.
• Collaborative office environment and frequent research discussions.

Hiring process

• Application review with emphasis on safety-relevant technical communication.
• Interviews and evaluations focused on red teaming, adversarial testing, and ability to translate findings into improvements.
• Use of AI in the application process follows the company’s candidate AI guidance policy.