AI Safety Red Team Engineer

Anthropic; California (MO); Hybrid; USD 320,000 - 405,000; Full time

Job summary

Anthropic is seeking a Red Team Engineer to help ensure the safety of our deployed AI systems and products. You will take an adversarial approach to uncover vulnerabilities across our product ecosystem before they can be exploited by malicious actors.

Your work will blend traditional security practices with AI safety concerns, including jailbreaking, abuse vectors, and novel attack chaining. You will collaborate with Product, Engineering, and Policy teams to translate findings into concrete

Qualifications

• Experience with 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 and hands-on experience with security testing tools such as Burp Suite or Metasploit.
• Experience building custom automation, including LLM-specific testing frameworks.
• A track record of discovering novel attack vectors and chaining vulnerabilities in creative ways.

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

Model jailbreaking

Agentic workflows testing

Communication skills

Education

Bachelor’s degree or equivalent

Tools

Burp Suite

Metasploit

Custom scripting frameworks

Job description

Anthropic is seeking a Red Team Engineer to help ensure the safety of our deployed AI systems and products. You will take an adversarial approach to uncover vulnerabilities across our product ecosystem before they can be exploited by malicious actors.

Your work will blend traditional security practices with AI safety concerns, including jailbreaking, abuse vectors, and novel attack chaining. You will collaborate with Product, Engineering, and Policy teams to translate findings into concrete