Collaborate with offensive security and engineering teams to validate AI security controls through targeted testing and technical assessments of AI systems against emerging threats including prompt injection, model manipulation, training data poisoning, insecure plugins, excessive agency, data leakage and supply-chain compromise. Research advances in AI/ML development, such as Agentic AI, Multimodal AI, Reasoning Models, AI Security and Governance, AI in Software Engineering, the AI regulatory landscape (EU AI Act, US SEC AI Compliance Plan, etc.) and AI/ML governance and security frameworks (ISO/IEC42001, NIST AI RMF, OWASP Top 10 for LLM Applications, OECD AI Principles, etc.).