← All roles

Red Team Engineer, Safeguards

Anthropic· Safeguards (Trust & Safety)
Apply on company site
Hybrid (San Francisco, CA)$320k - $405kFull-timePosted 3mo ago

About the role

Red Team Engineer role focused on adversarial testing to uncover vulnerabilities in Anthropic's deployed AI systems and products, emphasizing safety implications and novel abuse specific to advanced AI. Responsibilities span technical infrastructure vulnerabilities to emergent risks from AI capabilities, simulating sophisticated threat actors and developing scalable testing methodologies.

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

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
  • A public body of work such as CVEs, blog posts, or disclosed bug bounty reports
  • Strong written and verbal communication skills, with the ability to explain technical concepts to varied audiences

Skills

Required:Penetration testingModel jailbreaking / prompt injection testingWeb application securityAutomation / tooling for AI testingCommunication

Benefits

  • Competitive compensation and benefits
  • optional equity donation matching
  • generous vacation and parental leave
  • flexible working hours
  • office space for collaboration
Last updated Jul 15, 2026. Interested? Apply on the company site.

About Anthropic

building reliable, interpretable, and steerable AI systems

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

ai-infrastructure-and-developmentliquid-ai-recruiting-targetsetter-30setter-30-2026-q1wing-list-2026wing-list-2026-giga-stage
Company profileWebsite

More open roles at Anthropic