AI Security Engineer

AI Security Architecture & Guardrails:

• Define and evolve the enterprise AI Security Architecture, guardrails, and security requirements aligned to business objectives.
• Establish secure-by-design patterns across AI development, deployment, and operations, including hardening, hosting, access control, monitoring, and testing.
• Identify and mitigate AI-specific risks including data leakage, prompt injection, jailbreaks, model abuse, and AI supply-chain risk.

Platform & Engineering Enablement:

• Design and engineer security controls for AI-enabled SaaS applications, internal AI agents, model hosting, inference services, APIs, and orchestration layers.
• Secure RAG architectures, vector databases, embeddings, model training, fine-tuning pipelines, and MCP agent-to-agent interactions.
• Extend identity and access principles to non-human identities and autonomous agents with least-privilege and delegated authorization patterns.

Data Security Engineering:

• Design and enhance enterprise data security controls with a focus on AI-driven data access using Microsoft Purview.
• Implement data classification, sensitivity labeling, DLP, and information protection aligned to AI architectures.
• Support secure use of enterprise data in RAG pipelines, AI workflows, and training environments to prevent sensitive data exposure.