Description

Secure AI systems by implementing Zero Trust principles across RAG and AI Agents.

Responsibilities

• Design and enforce Zero Trust architecture for RAG and AI Agent security.
• Implement Azure Purview for AI policy enforcement and data governance.
• Define and implement prompt data security, red-teaming, and content safety filters.
• Manage agent access control, audit logs, and risk scoring mechanisms.
• Define Responsible AI frameworks, automated policy checks, and compliance dashboards.

Required Skills

• 8-12 years of experience in security engineering.
• Expertise with Azure security services: Entra, Purview, Key Vault, Private Networking.
• Experience with LLM security, jailbreak prevention, and content safety.
• Proficiency in Policy as Code and Role-Based Access Control (RBAC).
• Ability to design audit workflows for AI systems.
• Experience conducting threat modeling specifically for AI systems and agents.

Key Skills

Education

Any Gradute