Adversarial AI Security Engineer

Anthropic Limited; San Francisco (CA); Hybrid; USD 320,000 - 405,000; Full time

Job summary

Anthropic Limited in San Francisco is seeking a Red Team Engineer to identify vulnerabilities across our AI product ecosystem, using adversarial testing to simulate real-world threats.

You will build automated testing frameworks, collaborate with Product, Engineering, and Policy teams, and help establish metrics for detection of novel abuse. This role emphasizes safety and scale, with a focus on jailbreaking, prompt injection vectors, and guardrails beyond traditional security.

Qualifications

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

Responsibilities

• Conduct comprehensive adversarial testing across Anthropic's product surfaces, developing creative attack scenarios that combine multiple exploitation techniques.
• Research and implement novel testing approaches for emerging capabilities, including agent systems, tool use, and new interaction paradigms.
• Design and execute "full kill chain" attacks that emulate real-world threat actors attempting to achieve specific malicious objectives.
• Build and maintain systematic testing methodologies that evaluate every aspect of our systems.
• Develop automated testing frameworks to enable continuous assessment at scale.
• Collaborate with Product, Engineering, and Policy teams to translate findings into concrete improvements.
• Help establish metrics for measuring detection effectiveness of novel abuse.

Skills

Penetration testing

Red teaming

Application security

LLM testing frameworks

Vulnerability research

Communication skills

Education

Bachelor's degree in a relevant field

Tools

Burp Suite

Metasploit

Scripting frameworks

Job description

Anthropic Limited in San Francisco is seeking a Red Team Engineer to identify vulnerabilities across our AI product ecosystem, using adversarial testing to simulate real-world threats.

You will build automated testing frameworks, collaborate with Product, Engineering, and Policy teams, and help establish metrics for detection of novel abuse. This role emphasizes safety and scale, with a focus on jailbreaking, prompt injection vectors, and guardrails beyond traditional security.