Red Team Engineer — AI Safety & Adversarial Testing (Flexible Hours)

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

Benefits offered by this job

Equity donation matching

Generous vacation

Parental leave

Flexible working hours

Office space

Job summary

Anthropic is seeking a Red Team Engineer to uncover vulnerabilities across our AI product ecosystem. You will simulate adversaries, perform comprehensive adversarial testing, and explore novel abuse vectors in our deployed systems.

You will design kill-chain style attacks, build automated testing frameworks, and collaborate with Product, Engineering, and Policy teams to translate findings into concrete improvements for safer AI.

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 and security testing tools.

Responsibilities

• Conduct adversarial testing across Anthropic’s product surfaces with creative attack scenarios.
• Research and implement novel testing approaches for emerging AI capabilities.
• Design and execute full kill chain attacks emulating real threat actors.
• Build and maintain testing methodologies and automated frameworks for scalable assessment.
• Collaborate with Product, Engineering, and Policy teams to translate findings into improvements.
• Help establish metrics for detection effectiveness of novel abuse.

Skills

Penetration testing

Red teaming

Application security

Security tooling

LLM testing frameworks

Vulnerability research

Education

Bachelor's degree

Tools

Burp Suite

Metasploit

Custom scripting frameworks

LLM testing frameworks

Job description

Anthropic is seeking a Red Team Engineer to uncover vulnerabilities across our AI product ecosystem. You will simulate adversaries, perform comprehensive adversarial testing, and explore novel abuse vectors in our deployed systems.

You will design kill-chain style attacks, build automated testing frameworks, and collaborate with Product, Engineering, and Policy teams to translate findings into concrete improvements for safer AI.