Member of Technical Staff (Senior Security Researcher)
Core
Discover and exploit GenAI security vulnerabilities end-to-end to assess AI systems for cyber and national security risks.
Role type
Senior Security Researcher (GenAI Red Teaming)
Builds
Operational sprints for product groups and scalable AI Red Teaming methodologies
Domain
Cybersecurity, National Security, Generative AI
Deliverable
production ML models
Required skills
Penetration testing, Adversarial ML, Red teaming, Predictive analytics, Export control compliance, Python, C/C++, Kali Linux, Burpsuite, Nmap, Nessus
Preferred skills
Experience testing AI agents, Background in development
Technologies
Python, C#, C/C++, PowerShell, Kali Linux, Burpsuite, Nmap, Nessus
Responsibilities
Manage product group stakeholders for operational sprints, Develop methodologies to scale AI Red Teaming, Work alongside offensive security engineers and adversarial ML experts
Seniority
Senior, hands-on IC
