Red Team Engineer, Safeguards
Red Team Engineer on Anthropic's Safeguards team performing adversarial testing and full kill-chain attacks on AI products to uncover vulnerabilities, jailbreaks, and novel abuse vectors before malicious exploitation. Requires strong pen-testing, red teaming, and LLM-specific security experience.
About the job
Key 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.
Minimum 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.
Preferred Qualifications
- Experience with AI/ML security or adversarial machine learning.
- Understanding of AI safety considerations beyond traditional security, including modern guardrails against jailbreaks.
- Experience testing API security and rate-limiting systems.
- Background in testing business logic vulnerabilities and authorization bypass techniques.
- Background in anti-fraud, trust & safety, or abuse prevention systems.
- Familiarity with distributed systems and infrastructure security.
- Familiarity with abuse detection mechanisms and the ability to engineer novel bypasses.
- Adaptability to understand and build engagements around emerging threats outside your direct area of expertise.
Compensation
Annual Salary: $320,000—$405,000 USD
Education
- Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience.
- Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience.
Skills
Penetration Testing, Red Teaming, Application Security, Model Jailbreaking, Prompt Injection, Burp Suite, Metasploit, Web Application Security, Llm Testing Frameworks, Adversarial Machine Learning, Api Security, Distributed Systems Security
Similar jobs
Security Engineering jobs
Anthropic
New York, NYThis hands-on security engineer will research sophisticated threat actors, build intelligence pipelines, conduct threat hunts, analyze malware and infrastructure, and translate findings into durable detections. The role requires at least five years of cyber threat intelligence or related experience, strong Python engineering, and malware and detection-analysis expertise.
Anthropic
San Francisco, CASenior hands-on security engineer responsible for endpoint hardening, device trust, identity and SaaS governance, and scalable corporate-security automation across a growing organization. Requires endpoint security expertise, Python scripting, IAM and zero-trust depth, and strong threat-modeling judgment.
Anthropic
San Francisco, CAConduct offensive security operations, red-team engagements, penetration testing, and adversarial simulations across cloud, endpoint, and bare-metal environments. The role requires at least five years of experience, strong engineering skills, and expertise across multiple security domains.
Anthropic
San Francisco, CABuild and operate evaluations for cyber capabilities and safeguard robustness in AI models, analyze adversarial data, and develop cyber-abuse detection probes. The role requires hands-on cybersecurity experience, Python proficiency, evaluation expertise, and strong cross-functional communication.
OpenAI
San Francisco, CA
Design and ship security-critical software and firmware at the boundary between policy systems and hardware-backed cryptographic protection. The role requires 5+ years of secure embedded development and deep C, C++, or Rust experience.