Security Engineer, AI Security Frontier Risks

Meta Security is seeking a Frontier AI Cybersecurity Evaluation Engineer with experience in assessing and enhancing the security of AI systems. This role involves coordinating, executing, and driving remediations for cybersecurity evaluations focused on AI technologies. You will help the team establish, lead, and execute multi-year roadmaps to mature AI security, drawing upon cross-functional partnerships to deliver security posture reviews on a repeatable basis and review new AI systems as they're developed.

Security Engineer, AI Security Frontier Risks Responsibilities:

• Conduct cybersecurity evaluations and lead AI security assessments in a cross-functional environment, driving finding remediations
• Collaborate with different teams within the AI Security Group, Detection and Response organization, and Product Security Group to develop and offer holistic AI security solutions
• Develop initiatives that improve our capabilities to effectively evaluate AI systems to enhance the organization's prevention, detection, response, and threat hunting capabilities
• Refine operational metrics, key performance indicators, and service level objectives to measure AI Security services
• Influence and align the team's vision and strategy. Collaboratively prioritize and deliver specific multi-year roadmaps and projects
• Build, cultivate, and maintain effective relationships with internal customers to identify and facilitate solutions to increase the impact of the team's work
• Partner with cross-functional teams to solve challenges related to a broad spectrum of AI security initiatives
• Coach, mentor, support, and care for the team in a way that enables long-term career development, happiness, and success at scale

• 8+ years of work experience in offensive Cybersecurity evaluations in a large, regulated organization
• Be a technical and process subject matter expert regarding AI Security services, and attacker tactics, techniques, and procedures
• Experience developing and delivering information on AI security evaluations and program status for leadership
• Experience working with public threat intelligence reporting and internal threat intelligence teams to create and adapt AI security offerings to improve security programs of all maturity levels in a large organization
• Experience leading and managing complex cross-functional programs and teams
• Experience evaluating both external and insider threats
• Knowledge of AI technologies, machine learning models, and related protocols
• Coding and scripting experience in one or more general-purpose languages
• Bachelor's degree (or foreign degree equivalent) in Information Systems Engineering, Computer Science, Engineering, Information Security, Cyber Security, Information Assurance, or related field or equivalent work experience

• Experience in coding and breaking AI models or other machine learning systems
• Experience in code and infrastructure security reviews and threat modeling for AI systems
• Experience attacking AI, distributed, and/or p2p systems
• Broad knowledge across the Security domain, as well as demonstrated focus in AI security evaluations and in one (or more) areas of Cybersecurity such as Red Teaming, Purple Teaming, Vulnerability Research, and Exploitation
• Master's degree (or foreign degree equivalent) in Information Systems Engineering, Computer Science, Engineering, Information Security, Cyber Security, Information Assurance, or related field