AI Security Specialist
Core
Senior AI security subject matter expert and technical lead responsible for building, implementing, and maintaining an AI security program, providing strategic guidance on protecting AI systems, machine learning models, and AI-enabled applications.
Role type
Senior IC AI Security Specialist (Subject Matter Expert)
Builds
AI security program, policies, standards, risk-management frameworks, testing frameworks, and evaluation criteria for federal AI systems.
Domain
Federal Government / AI Security / Cybersecurity
Deliverable
production ML models
Required skills
AI/ML security, adversarial machine learning, model poisoning, adversarial attacks, model inversion, data integrity threats, backdoor attacks, membership inference, data poisoning, federal AI governance frameworks, NIST AI Risk Management Framework, Executive Orders 13960 and 14110, CISSP, CISM, AI/ML concepts, architectures, and development methods, AI security risk-assessment methods, MLOps pipelines, generative AI security, large language model security, prompt injection, data leakage, model abuse, AI governance materials, privacy and data governance, federal cybersecurity frameworks (NIST SP 800-53, FISMA), AI red teaming, adversarial robustness testing, AI penetration testing
Preferred skills
Masters degree or Ph.D. in cybersecurity, computer science, artificial intelligence, data science, AI security subject matter expert or advisor experience, Certified Artificial Intelligence Security Specialist (CAISS), AI red teaming, adversarial robustness testing, AI penetration testing
Technologies
AI Support Machine Learning MLOps Model Training Security
Responsibilities
Act as senior AI security subject matter expert and technical lead, providing strategic guidance on protecting AI systems, machine learning models, and AI-enabled applications. Build, implement, and maintain the AI security program, including policies, standards, guidance, and risk-management frameworks aligned with federal requirements. Lead security risk assessments and reviews of AI systems and initiatives; evaluate AI-specific threats and develop mitigation strategies. Provide security oversight across the AI system lifecycle, integrating requirements from planning and design through development, testing, deployment, and operation. Create and maintain methods, testing frameworks, and evaluation criteria for assessing AI system and model security and trustworthiness. Work with data science, AI development, and application teams to incorporate security practices, secure development guidance, and testing requirements into their workflows. Lead preparation of AI governance materials, including use-case inventories, impact assessments, system security plans, and other required documentation. Track emerging AI threats, vulnerabilities, attack techniques, and federal guidance, and provide timely assessments and recommendations to security leadership. Advise on generative AI and large language model security, and develop policies and guidance for their secure and responsible use. Partner with the privacy team to address AI-related privacy risks, data minimization, and the privacy effects of model training, deployment, and outputs. Integrate AI security into cybersecurity frameworks, risk processes, and authorization activities, including AI-specific control overlays and assessment procedures. Represent the SBA as a technical expert in AI security engagements with OMB, CISA, NIST, and other federal partners. Develop and deliver AI security awareness and training for personnel and contractors. Lead or support reviews after AI security incidents and near-misses, turning lessons learned into improvements to the program and practices. Prepare AI security briefings, program reports, and strategic recommendations for senior leaders and oversight bodies. Keep current with AI security research, technology, federal policy, and industry practices, applying relevant developments to strengthen the program.
Seniority
Senior, hands-on IC and strategic lead
