AI Security Engineer

Position Overview

The AI Security Engineer role demands an experienced professional responsible for safeguarding AI and machine learning platforms, especially within Azure and other cloud environments. This position includes engineering and verifying security controls to protect sensitive data, identities, models, and AI infrastructure throughout the lifecycle.

Education and Qualifications

• Bachelor's degree in Computer Science, Cybersecurity, Information Technology, Information Systems, Engineering or equivalent.
• Advanced degree in information or cybersecurity is considered a plus.

Experience and Certifications

• At least 5 years of cybersecurity engineering practice, focusing on cloud security, application security, or data security with hands-on experience in AI/ML or agentic AI technologies.
• Certifications such as Microsoft Azure security/AI certifications (SC-100, AZ-500, AI-102) or their equivalents.
• Preferred certifications include CISSP, CCSP, CISM.
• Training in AI security or ML security, with knowledge of OWASP Large Language Model (LLM) security.
• Advantageous to hold Kubernetes Security Specialist (CKS) or DevSecOps certifications.

Core Skills and Expertise

• Securing Azure AI, OpenAI, ML environments, and cloud-native controls.
• Implementing Identity and Access Management (IAM), managed identities, API security, secrets management, and network isolation.
• Expertise in AI threat modeling, prompt injection testing, and securing Retrieval-Augmented Generation (RAG) architectures.
• Data Security Posture Management (DSPM), Data Loss Prevention (DLP), data classification, and compliance with regulated data protection standards.
• Scripting proficiency with Python and PowerShell for CI/CD pipelines and security automation.

Primary Responsibilities

• Maintain comprehensive inventory of AI/ML assets including models, inference endpoints, agents, connectors, training pipelines, and infrastructure.
• Conduct security assessments of Azure AI services, Azure OpenAI, Azure Machine Learning, and authorized third-party AI platforms.
• Evaluate authentication, authorization, managed identities, service principals, API keys, secrets, network exposure, and rate-limiting safeguards.
• Implement and verify least-privilege RBAC, private network endpoints, firewall configurations, encryption protocols, and secure secret storage.
• Analyze AI data flows for Personally Identifiable Information (PII), Protected Health Information (PHI), and sensitive data exposure in prompts, outputs, repositories, connectors, and training data.
• Configure or audit content safety features including filters, prompt guardrails, custom blocklists, and abuse prevention mechanisms.
• Test for vulnerabilities including prompt injection, jailbreaks, improper output handling, excessive autonomy, data leaks, model misuse, and integration abuse.
• Review permissions in model registries, ensure model/version integrity, track dependencies, and secure the AI supply chain.
• Create AI-specific logging, monitoring, and anomaly detection for API misuse, prompt attacks, privilege abuse, and data leaks.
• Support identification and control of Shadow AI through CASB/SWG tools, endpoint protections, and cloud monitoring.
• Lead threat modeling and security testing for AI use cases before production launch and upon significant changes.
• Manage AI security issues including findings, risks, exceptions, and remediation through to resolution, supporting risk acceptance as needed.
• Prepare detailed AI security assessment reports, data exposure findings, control validation evidence, and maturity level recommendations.
• Collaborate closely with AI Governance, Privacy, Legal, Data, Cloud, Application Security, Security Operations Center, and business stakeholders.