AI Security SME

About the role

This role leads the security architecture, governance and assurance of AI and GenAI platforms across the organization, covering classical ML systems and modern LLM and agentic architectures. You will define how models are designed, deployed, monitored and defended so that they are robust, explainable, privacy-preserving and compliant, and act as the go-to expert for AI security across products, data, cloud and security teams.

Key responsibilities

• Design and review secure architectures for ML/LLM workloads (training, fine-tuning, inference, RAG, agents, plugins, tool calling, APIs) and define reference architectures for on-prem, hybrid and cloud platforms.
• Perform AI-specific threat modeling (data poisoning, model theft, prompt injection, jailbreaks, supply chain, inference attacks) and align controls with NIST AI RMF, ISO/IEC 27001, ISO/IEC 42001, OWASP GenAI/LLM Top 10, MITRE ATLAS and others.
• Define and oversee controls for data pipelines, model integrity, access control, secure prompt engineering, guardrails, data classification, masking and DLP, and MCP server hardening.
• Work with engineering and data science to embed robustness, observability and evaluation pipelines, and contribute to SLOs/SLAs for AI systems.
• Embed AI security in CI/CD, including scanning, dependency checks, policy-as-code and red-teaming before and after release.
• Run red teaming, develop AI-specific incident response playbooks and lead or support red/blue/purple teaming exercises.
• Advise on AI regulations and standards (e.g. EU AI Act), define internal responsible AI policies, and run workshops and training for stakeholders.

Required profile

• 8-12+ years in cybersecurity, with 3-5+ years focused on AI/ML or data platforms.
• Proven track record designing or reviewing secure architectures for ML pipelines, LLM/RAG systems or agentic platforms.
• Strong understanding of cryptography, IAM, network and application security, and data protection and privacy (PII, PHI, DPIA).
• Excellent communication skills, able to translate complex AI risks into business and technical requirements.

Required skills

• Cloud platforms (Azure, AWS, GCP) and at least one agentic/GenAI stack (Transformers, LangChain/LlamaIndex, vector DBs, MLOps).
• Frameworks such as NIST AI RMF, ISO/IEC 27001, ISO/IEC 42001, SOC 2, OWASP Top 10, MITRE ATT&CK/ATLAS, CSA MAESTRO.
• Certifications such as CISSP, CISM, CCSP, CCSK, AWS/Azure/GCP security specialties, and ideally CAISP or AI red teaming training.
• Desirable: Python scripting, Kubernetes, zero trust, logging and tracing, and formal training in secure MLOps, privacy engineering and OWASP GenAI/LLM Top 10.