Principal AI Security Engineer

Key Responsibilities

• AI Security Architecture & Engineering
  • End-to-End Security: Design and implement secure-by-design architectures for the entire AI lifecycle, including data ingestion, model training, fine-tuning, and inference.
  • Azure AI Specialist: Lead the security configuration for Azure OpenAI Studio, Azure AI Foundry, and Azure AI Search, ensuring enterprise-grade protection.
  • Hands-on Implementation: Develop and deploy security controls, including prompt injection mitigations, rate limiting, and content filtering.
  • MCP Integration: Securely implement and oversee Model Context Protocol (MCP) to facilitate safe communication between AI models and local/remote data sources.
• Governance & Compliance
  • Framework Ownership: Establish and maintain AI security standards based on global frameworks (e.g., NIST AI RMF, ISO/IEC 42001, OWASP Top 10 for LLMs).
  • Policy Development: Draft enterprise-wide policies for responsible AI usage, data privacy, and model risk management.
• Identity & Data Security
  • Architect sophisticated identity management for AI agents (Workload Identities) and ensure data-at-rest/motion is encrypted and permissioned via Azure RBAC and Entra ID.
• Guardrails & Monitoring
  • Control Building: Build automated guardrails to prevent data leakage and ensure model outputs remain within ethical and legal boundaries.
  • Threat Modeling: Conduct AI-specific threat modeling and red-teaming exercises to identify vulnerabilities in RAG (Retrieval-Augmented Generation) patterns.
  • Observability: Partner with the SOC to develop monitoring dashboards for AI-related anomalies and security events.

Required Qualifications

• Experience: 10+ years in Cybersecurity, with at least 3+ years focused specifically on AI/ML Security.
• Azure Expertise: Proven track record securing Azure OpenAI, Azure AI Search, and Azure Foundry.
• Technical Depth: Deep understanding of LLM vulnerabilities (Prompt Injection, Insecure Output Handling, Training Data Poisoning).
• Data Security: Expertise in securing data workflows for AI, including vector database security and sensitive data masking.
• Governance: Extensive knowledge of AI Governance frameworks and the regulatory landscape (EU AI Act, etc.).
• Technical Skills & Tools: Platforms: Azure AI Studio, Azure Machine Learning, Azure Kubernetes Service (AKS); AI Protocols: Experience with Model Context Protocol (MCP) and API security (REST, gRPC); Languages: Proficiency in Python and PowerShell/Bash for automation and security tooling; Identity: Expert-level knowledge of Azure Entra ID (formerly Azure AD) and Managed Identities for AI workloads.