Director, AI Security

This is a fully remote position, open to applicants in New Jersey.

📋 Description

• Develop and expand enterprise AI security capabilities encompassing models, harnesses, agents, end-user AI utilization, supply chains, runtime protection, assurance, observability, and applications.

• Implement AI discovery to recognize enterprise applications of generative AI, agents, models, and prioritize security vulnerabilities.

• Manage end-user AI usage, enforcing access controls and data protection measures.

• Oversee AI agent identity and authorization security, covering non-human identities, credentials, service accounts, and least-privilege permissions.

• Incorporate security testing and protective measures throughout the AI development, deployment, and operational phases.

• Establish AI onboarding and assurance processes, including model assessments, agent evaluations, red-team guidance, supply-chain assurance, and runtime monitoring.

• Set production security approval criteria for AI models, agents, applications, and advanced capabilities.

• Apply controls to prevent model/data poisoning, compromised components, and model exposures.

• Ensure ongoing adversarial testing for prompt injection and other significant threats; validate defenses and remediation strategies.

• Integrate AI telemetry and detections into security operations, collaborating on detection, triage, and incident response.

• Deploy advanced models to identify and prioritize cybersecurity vulnerabilities, accelerating investigations and expediting remediation with safeguards and human validation.

• Collaborate with AI Governance, Privacy, Architecture, Risk Management, Cyber Defense, GSO, IAM, Vulnerability Management, Application Security, and business teams.

• Manage relationships with AI security vendors, including budget oversight, vendor selection, performance management, and capability rationalization.

• Drive prompt remediation of AI-related vulnerabilities.

• Lead standards adoption, control-effectiveness evaluation, executive risk communication, roadmap development, and investment planning.

• Build and mentor an enterprise AI security team.

⛳️ Requirements

• Bachelor's degree in Information Security, Computer Science, Engineering, Information Systems, or a related field, or equivalent experience.

• Over 12 years of progressive experience in cybersecurity, application security, security engineering, or related fields.

• Recent hands-on experience securing AI-enabled systems.

• Experience in implementing, managing, and scaling AI security capabilities across generative AI services, applications, agents, and models.

• Sound understanding of AI/ML lifecycles, LLMs, RAG, model APIs, and agent tool integrations.

• Expertise in AI discovery, identity and access enforcement, least-privilege agent permissions, secrets protection, DLP, and runtime safeguards.

• Ability to evaluate and mitigate prompt injection, sensitive data exposure, excessive agency, tool misuse, insecure output handling, model theft, adversarial manipulation, poisoning, and AI supply-chain compromise.

• Experience in cloud and platform security.

• Proven experience integrating AI security telemetry with security operations and incident response.

• Familiarity with detection engineering, investigation, containment, and remediation.

• Ability to lead technical security teams and manage vendors, budgets, and concurrent capability deployments.

• Experience collaborating across engineering, security operations, and business stakeholders in a global, matrixed organization.

• Strong skills in executive stakeholder management, technical judgment, and communication.

• Preferred experience with production multi-agent systems and MCP integrations.

• Preferred experience in evaluating open-weight and fine-tuned models, adversarial evaluation suites, NIST AML guidance, MITRE ATLAS, and OWASP AI security guidance.

• Preferred experience integrating AI security into software delivery and MLOps pipelines.

• Preferred experience in advanced ML engineering, frontier model research, or adversarial AI research.

• Working knowledge of NIST AI RMF, OWASP LLM/agentic security guidance, and MITRE ATLAS.

• Preferred experience applying frontier AI to cybersecurity use cases.

• Preferred experience scaling AI security in regulated healthcare, pharmaceutical, or MedTech environments.

• Preferred contributions to the AI security field through disclosed vulnerabilities, research, open-source tools, or industry initiatives.

• Experience with skill security and multi-turn agentic security.

• Preferred certifications include CISSP, CISM, or equivalent; GAIPS, GASAE, or AAISM are particularly desirable.

🏝️ Benefits

• Pension plan.

• 401(k) savings plan.

• Long-term incentive program.

• Vacation – 120 hours per calendar year.

• Sick time – 40 hours per calendar year; 48 hours for Colorado residents; 56 hours for Washington residents.

• Holiday pay, including Floating Holidays – 13 days per calendar year.

• Work, Personal and Family Time – up to 40 hours per calendar year.

• Parental Leave – 480 hours within one year of birth/adoption/foster care of a child.

• Bereavement Leave – 240 hours for an immediate family member; 40 hours for an extended family member per calendar year.

• Caregiver Leave – 80 hours in a 52-week rolling period.

• Volunteer Leave – 32 hours per calendar year.

• Military Spouse Time-Off – 80 hours per calendar year.

• Inclusive interview accommodations.

• Equal opportunity employment.