AI Security Associate Manager
Core
Validate compliance with internal AI security, Responsible AI, and data protection requirements using established frameworks, checklists, and AI testing tools within the Cyber Risk team.
Role type
Associate Manager, AI Security
Builds
Security review criteria, reusable scripts, and updated testing frameworks for GenAI ecosystems
Domain
US Federal Government / AI Security / Cyber Risk
Required skills
GenAI ecosystem knowledge (LLMs, vector databases, prompt frameworks, agent orchestration), AI attack vector analysis (prompt injection, data leakage, model inversion, jailbreaking), AI security testing tool proficiency, cloud security fundamentals (Azure/AWS/GCP), Python/JS scripting, Responsible AI principles, technical writing, threat modeling
Preferred skills
Experience updating AI security patterns and guidance, experience with autonomous system behavior analysis
Technologies
LLMs, vector databases, prompt frameworks, agent orchestration, Azure, AWS, GCP, Python, JS
Responsibilities
Validate compliance with AI security and data protection requirements using frameworks and testing tools; Document findings including non-compliance and recommended mitigations; Monitor updates to AI platforms and models to ensure test coverage; Contribute to process improvements, reusable scripts, and security review criteria; Perform light threat modeling of AI-enabled workflows; Assess security impact of new AI features or model updates.
Seniority
Associate Manager, hands-on IC with team leadership
