About the role
We are seeking an experienced and hands-on AI Security Professional to establish and strengthen the organisation's AI security posture. The ideal candidate will possess deep expertise in securing artificial intelligence (AI), generative AI (GenAI), large language models (LLMs), AI applications, and machine learning (ML) systems throughout their lifecycle. This role will be responsible for developing AI security governance frameworks, conducting AI threat assessments, implementing technical controls, securing AI development pipelines, and ensuring compliance with regulatory and privacy requirements. The candidate should have practical experience in identifying and mitigating AI-specific threats such as prompt injection, model poisoning, adversarial attacks, data leakage, insecure plugins, model theft, and supply chain risks.
The core responsibilities for the job include the following:
AI Security Strategy and Governance:
- Develop and implement the organisation's AI security strategy and roadmap.
- Establish AI Security Policies, Standards, and Procedures.
- Define secure AI adoption frameworks aligned with the NIST AI Risk Management Framework (AI RMF), OWASP Top 10 for LLM Applications, OWASP Machine Learning Security Top 10 ISO/IEC 42001 ISO/IEC 23894 NIST Cyber Security Framework, RBI and other regulatory requirements (preferred).
Secure AI/ML Development Lifecycle:
- Implement Secure AI Development Lifecycle (SAI-SDLC).
- Integrate security controls into AI/ML pipelines and MLOps processes.
- Conduct security reviews of LLM applications, RAG architectures, AI agents, model APIs, AI plugins and extensions.
- Review AI architectures from a security and privacy perspective.
AI Security Assessments and Testing:
- Perform hands-on assessments including AI threat modelling, LLM security assessments, AI red teaming exercises, prompt injection testing, jailbreak testing, model extraction testing, model poisoning assessments, adversarial ML testing, AI API security reviews, AI supply chain security assessments, and AI infrastructure security reviews.
- Security assessments of AI agents and autonomous systems.
Security Controls Implementation:
- Design and implement controls including AI guardrails, prompt filtering, input/output validation, data loss prevention (DLP), AI gateway security, model access controls, secrets management, data classification and privacy controls, AI monitoring and logging, model integrity controls, human-in-the-loop controls, and secure RAG implementation practices.
AI Security Operations:
- Monitor AI systems for security threats and abuse.
- Develop AI-specific detection and response use cases.
- Build monitoring for prompt abuse, data exfiltration, model misuse, unauthorised model access, hallucination and manipulation attempts.
- Conduct incident investigations involving AI systems.
AI Risk and Compliance:
- Conduct AI risk assessments and privacy impact assessments.
- Establish AI governance processes.
- Define AI security review and approval mechanisms.
- Ensure compliance with privacy regulations and industry standards.
- Support audits and regulatory examinations.
Third-Party AI Risk Management:
- Assess security of AI vendors and SaaS AI platforms.
- Evaluate the following: ChatGPT Enterprise, Claude, Microsoft Copilot, Google Gemini, AI coding assistants, AI APIs and models.
- Conduct AI vendor due diligence and contract reviews.
Requirements:
- 7-12 years of overall cybersecurity experience.
- Minimum 3 years of dedicated hands-on experience in AI/ML security or GenAI security.
- Demonstrated experience in securing enterprise AI deployments.
- Experience conducting AI security assessments and red teaming engagements.
- Experience implementing AI governance and security controls in regulated industries such as BFSI is highly preferred.
AI and GenAI Security:
- Strong understanding of large language models (LLMs), generative AI, retrieval-augmented generation (RAG), AI agents, prompt engineering, AI model lifecycle, and agentic AI security.
- Hands-on security experience in prompt injection attacks, adversarial machine learning, AI red teaming, LLM vulnerability assessments, secure AI architecture reviews, AI application penetration testing, model security assessments, AI supply chain security, data privacy in AI systems, and AI security monitoring.
- Technical experience with Python, LangChain, LangGraph, LlamaIndex, OpenAI APIs, Anthropic APIs, Hugging Face, Docker, Kubernetes, GitHub/GitLab, cloud platforms (AWS/Azure/GCP), SIEM tools, and security testing tools.
- Preferred Security Tools Experience in NVIDIA NeMo Guardrails, Lakera AI, Protect AI, HiddenLayer, Microsoft AI Security tools, Palo Alto AI Security, Promptfoo, Garak, PyRIT, and OWASP GenAI security tools.
- Certifications (Preferred): Certified Information Systems Security Professional (CISSP), Certified Cloud Security Professional (CCSP), GIAC Machine Learning Engineer (GMLE), Certified AI Security Practitioner (CAISP), ISO/IEC 42001 Lead Implementer, Azure AI Engineer Associate, AWS Machine Learning Speciality, and Offensive Security certifications (OSCP/OSWE) are preferred.