Description

You will design and validate secure architectural patterns for AI agent integration, ensuring data privacy and IP protection within a regulated environment.

Responsibilities

• Evaluate AI tools, frameworks, and LLM providers to assess security posture and suitability.
• Conduct deep-dive threat modeling for AI-specific risks including prompt injection, model inversion, and data poisoning.
• Assess security capabilities of Azure AI Foundry, M365 Copilot Studio, and Microsoft Graph API against compliance standards.
• Design isolation strategies for Model Context Protocol (MCP) and develop hardening checklists for AI platforms.
• Implement advanced logging, auditing, and monitoring for AI agent telemetry to maintain visibility into autonomous actions.
• Lead the creation of AI Agent Security Design Principles and assist in authoring technical governance policies.
• Identify and bridge control gaps within existing CI/CD pipelines to support secure AI deployments.

Required Skills

• 5+ years of experience in Cloud Security or Architecture.
• Deep hands-on experience with the Azure platform.
• Direct experience with Azure AI Services, Azure OpenAI, and Azure AI Foundry.
• Expert-level understanding of Microsoft Entra ID, Service Principals, and Managed Identity.
• Deep familiarity with Model Context Protocol (MCP) regarding data isolation and session security.
• Strong grasp of Retrieval-Augmented Generation (RAG) patterns and vector database security.
• Proven track record implementing Zero Trust controls in financial services or cloud-native environments.
• Experience with Infrastructure as Code using Terraform or Bicep.
• Familiarity with OWASP Top 10 for LLMs and AI-specific vulnerability scanning.

Preferred Skills

• Azure Security Engineer Associate, Azure AI Engineer Associate, CISSP, or CCSP certifications.

Key Skills

Education

Any Gradute