Novel Abuse Red Teamer
Core
Design, execute, and refine adversarial testing and simulation protocols to uncover novel abuse vectors and strengthen AI product defenses against real-world threats.
Role type
Senior IC application security red teamer
Builds
Detection mechanisms and overall security posture for AI products
Domain
AI safety and application security
Deliverable
production ML models
Required skills
application security, penetration testing, red teaming, web application security, Burp Suite, Metasploit, attacker mindset, automation tool development
Preferred skills
testing of AI systems, identifying novel abuse vectors in live environments, cross-functional collaboration, continuous learning
Technologies
Burp Suite, Metasploit
Responsibilities
Design and execute high-fidelity attack simulations, analyze testing outcomes to refine detection mechanisms, develop automation tools for testing workflows, collaborate with security, product, and policy teams
Seniority
Senior, hands-on IC
