Lead AI security initiatives with our elite AI Red Team, focusing on enterprise-scale AI products for major organizations. Leverage your production experience to enhance system resilience and governance.
As a Principal Engineer, you will drive adversarial testing and threat modeling of advanced AI systems. This position merges skills in adversarial machine learning with knowledge of enterprise security architecture. You'll develop structured engagements, mapping vulnerabilities to ISO compliance while working closely with engineering and security teams.
Key Responsibilities:
• Design and execute adversarial tests on AI systems
• Conduct comprehensive threat modeling across data and infrastructure
• Oversee testing including prompt injection and model exploitation
• Translate findings into audit-ready documentation
• Present security insights to executive leaders
Requirements:
• Expertise in adversarial machine learning and LLM red teaming
• Proficient in P...