Manager, AI Security
Responsibilities
Lead and deliver client engagements focused on AI security, governance, and risk management across generative AI and agentic AI platforms, including Microsoft Copilot, OpenAI, Anthropic Claude, and emerging AI technologies.
Advises clients on secure AI adoption by designing and implementing AI security architectures, governance frameworks, guardrails, monitoring capabilities, and controls that enable responsible and scalable use of AI.
Assesses and strengthens the security of AI applications, agents, copilots, and supporting ecosystems by evaluating identity, access, data protection, model security, and operational risk.
Designs and implements security controls for agentic AI environments, including Model Context Protocol (MCP) security, non-human identities, AI agents, delegated permissions, and secure interactions between AI systems and enterprise applications.
Leads AI security testing activities, including assessments for prompt injection, jailbreak techniques, data leakage, model misuse, excessive permissions, and other emerging AI threats, while providing strategic remediation recommendations.
Supervises, mentors, and develops professionals across AI security engagements; contributes to solution development, thought leadership, market offerings, and practice growth initiatives while fostering a high-performing team environment.
Acts with integrity, professionalism, and personal responsibility to uphold KPMG's respectful and courteous work environment.
Qualifications
Minimum five years of recent experience in cybersecurity, IAM, application security, cloud security, AI governance, AI security, or related disciplines; and two years of AI Security experience.
Bachelor's degree from an accredited college/university in computer science, information security, information systems, engineering, or a related field is required.
Strong experience securing generative AI and agentic AI platforms, including AI governance, AI security architecture, secure AI solution development, and implementation of AI guardrails and security controls.
Experience with AI platform security and configuration, including technologies such as Microsoft Copilot, OpenAI, Anthropic Claude, or similar enterprise AI platforms.
Demonstrated knowledge of MCP (Model Context Protocol) security, AI agent security, agentic AI control frameworks, and Identity & Access Management (IAM), including management of human and non-human identities.
Experience designing and implementing Role-Based Access Control (RBAC), least-privilege access models, AI logging, monitoring, auditability, observability, and security controls to support regulatory and governance requirements.
Excellent written and verbal communication, facilitation, presentation, and client relationship skills with the ability to gain the confidence and respect of senior executives, lead delivery teams, and develop innovative AI security solutions for complex client environments.
Must be authorized to work in the U.S. without the need for employment-based visa sponsorship now or in the future.