Join our dynamic AI Security practice to lead the charge in securing AI and GenAI systems. This role is pivotal in conducting adversarial testing, safeguarding AI components throughout their lifecycle, and implementing robust security controls within enterprise environments. You will be instrumental in building an exceptional experience in AI-driven cyber defense.

EY is dedicated to building a better working world. We leverage data and technology to foster trust and help clients grow and transform.

Lead AI red teaming exercises, including sophisticated prompt injection, jailbreak, and data exfiltration scenarios. Conduct comprehensive AI threat modeling across model, data, and application layers. Design and deploy LLM guardrails and RAG security controls to enhance protection. Perform thorough security reviews of ML pipelines and the entire model lifecycle. Secure critical APIs and AI inference endpoints within cloud infrastructure. Provide expert support for incident response related to AI-specific threats and exploitation attempts.

Integrate essential security controls into AI/ML pipelines and DevSecOps workflows. Collaborate closely with SOC teams to develop effective AI workload detection and monitoring use cases.

A minimum of 3-6 years of experience in cybersecurity, application security, or cloud security is essential. Demonstrable hands-on exposure to AI/GenAI security concepts or implementation is required. Proven experience in vulnerability assessment, red teaming, or threat modeling is crucial. Familiarity with cloud platforms such as Azure or AWS is expected.

We seek a self-driven cybersecurity professional with deep technical expertise in AI security, capable of independently driving security testing and implementation for enterprise AI workloads.