Join EY's AI Security practice and become a leader in securing AI/GenAI systems. This role involves spearheading adversarial testing and implementing robust controls for AI components throughout their lifecycle within enterprise environments. Build a career at EY, where you'll have the global scale, support, and inclusive culture to excel.

Lead AI red teaming initiatives, including complex scenarios like prompt injection and data exfiltration. Conduct thorough AI threat modeling across model, data, and application layers. Design and implement advanced LLM guardrails and RAG security controls. Perform security reviews for ML pipelines and model lifecycles. Secure critical APIs and AI inference endpoints in cloud infrastructures. Assist in incident response for AI-specific threats and exploitation attempts. Integrate security controls into AI/ML pipelines and DevSecOps workflows, and collaborate with SOC teams for AI workload detection and monitoring.

Requires 3-6 years of dedicated experience in cybersecurity, application security, or cloud security. Demonstrable hands-on exposure to AI/GenAI security concepts or implementations is essential. Proven experience in vulnerability assessment, red teaming, or threat modeling is also crucial. A working knowledge of major cloud platforms such as Azure or AWS is necessary. Ideally, candidates will possess hands-on experience with AI security tools like Garak, PyRIT, or LLM Guard, and exposure to adversarial ML tools. Experience integrating security into MLOps/DevSecOps pipelines and relevant security or cloud certifications are highly valued.