About the role
We are seeking an experienced AI Security Professional to secure, assess, and govern AI agents and multi-agent systems across enterprise environments. The ideal candidate will have expertise in AI security, cybersecurity, cloud security, and secure software development, with a strong understanding of emerging threats specific to Large Language Models (LLMs), AI agents, and autonomous systems.
Responsibilities:
- Perform security architecture reviews for AI-powered systems.
- Assess AI infrastructure against OWASP Top 10 for LLM Applications, MITRE ATLAS, and other AI security frameworks.
- Identify and mitigate risks such as prompt injection, jailbreak attacks, indirect prompt injection, model poisoning, data leakage, and unauthorised tool execution.
- Implement guardrails, policy enforcement, and runtime monitoring for AI agents.
- Secure integrations between AI agents, APIs, enterprise applications, cloud services, and databases.
- Stay current with emerging AI attack techniques, vulnerabilities, security research, and regulatory developments.
Requirements:
- Agentic AI Architectures and Autonomous AI Systems Retrieval-Augmented Generation (RAG) Security AI Guardrails and Policy Enforcement AI Model Lifecycle Security OWASP Top 10 and OWASP Top 10 for LLM Applications AI Security Tools and Threat Detection Platforms AWS, Azure, or Google Cloud Security Docker and Kubernetes Security Infrastructure as Code (Terraform, CloudFormation, Bicep) NIST AI RMF, ISO/IEC 42001 ISO 27001 and NIST Cybersecurity Framework.