Girish rao

Led enterprise AI/ML security risk assessments covering model integrity, bias, explainability, data leakage, and adversarial threats. Designed ISO/IEC 42001 AIMS and operationalized NIST AI RMF, mapping controls to EU AI Act and OECD AI Principles. Built STRIDE/MITRE ATLAS threat modeling and LLM red teaming using Garak/PyRIT. Architected secure Azure OpenAI RAG and agentic AI controls, and assessed Azure AI Foundry, AWS SageMaker, and Google Vertex AI security.