Red Team Engineer, Safeguards
Core
Conduct adversarial testing and red teaming to uncover vulnerabilities in AI systems, products, and infrastructure before malicious exploitation.
Role type
Red Team Engineer (AI Safety)
Builds
Automated testing frameworks and systematic methodologies for evaluating AI product surfaces and emergent capabilities.
Domain
AI Safety / Cybersecurity / Large Language Model Security
Deliverable
production ML models | product features
Required skills
Penetration testing, model jailbreaking, prompt injection testing, web application security, custom automation, LLM-specific testing frameworks, vulnerability chaining, technical writing
Preferred skills
Adversarial machine learning, API security, rate-limiting testing, business logic vulnerabilities, anti-fraud systems, distributed systems security, abuse detection engineering
Technologies
Burp Suite, Metasploit, custom scripting frameworks
Responsibilities
Develop creative attack scenarios combining multiple exploitation techniques, research novel testing approaches for agent systems and tool use, design and execute full kill chain attacks, build automated testing frameworks for continuous assessment, collaborate with cross-functional teams to translate findings into improvements, establish metrics for detection effectiveness
Seniority
Mid-Senior, hands-on IC