Join EY and build a career that's as unique as you are. Leveraging global scale, supportive culture, and advanced technology, you'll have the opportunity to become your best self. Your distinct voice and perspective are crucial in helping EY achieve even greater success and contribute to a better working world for everyone.

This Manager role within the AI & SaaS Product Security, Strategic Platforms and AI Security service line presents an exciting opportunity. You will lead the design and implementation of robust, multi-layered defense architectures for enterprise AI and GenAI systems. The focus is on securing AI across its data, model, and application layers, while also driving comprehensive, end-to-end AI security programs.

As a key leader, you will be responsible for architecting layered defense systems for AI across data, model, and application/runtime layers. You will spearhead end-to-end AI security initiatives, encompassing assessments, implementation, and ongoing governance. Establishing and enforcing AI guardrails, access controls, and governance frameworks will be a core duty. Furthermore, you'll drive AI threat modeling and adversarial testing strategies throughout the AI lifecycle, oversee AI red teaming programs, and ensure continuous testing of AI systems.

Your role will also involve integrating AI security measures with SOC, SIEM, cloud security, and identity platforms. You will champion the adoption of secure MLOps / MLSecOps within enterprise environments. Engaging with stakeholders to evaluate AI risk exposure and propose effective mitigation strategies is essential. Providing expert architectural guidance for securing APIs, model endpoints, and AI pipelines will also fall under your purview.

To excel in this role, a strong architectural mindset coupled with proven experience in designing defense-in-depth solutions is essential. You should possess a deep understanding of AI/ML systems, Large Language Models (LLMs), and enterprise AI architectures. Comprehensive knowledge of cloud security, Zero Trust principles, and identity security is required. Experience in threat modeling, red teaming, and adversarial security practices is critical.

An understanding of AI attack surfaces and exploit patterns will be highly beneficial. The ability to seamlessly integrate security into DevSecOps and MLOps pipelines is a must. Excellent stakeholder management and client engagement skills are also vital. Candidates should have 6–10 years of experience in cybersecurity, cloud security, or application security, with a track record of solutioning and delivering security architecture programs. Hands-on exposure to AI/GenAI systems and their associated security controls, along with experience working with enterprise cloud platforms like Azure or AWS, is expected.