SME - IT Security

Job Summary

Job Description - Agentic AI Security Specialist Function: CSO Role: Agentic AI Security Specialist Hiring Managers: Louise Furniss / Julie Wilson Grade: E/F Location: UK / Offshore Open Positions: 2 Duration: 10 Months ________________________________________ Job Summary • Join the Cyber Security organization to secure next-generation Agentic AI, Generative AI, and autonomous AI systems across the enterprise. • Provide specialist security expertise for AI agents, Large Language Models (LLMs), and intelligent workflow orchestration platforms. • Partner with AI engineers, architects, data scientists, and security teams to embed security throughout the AI lifecycle. • Design and implement controls to protect AI systems from emerging threats, adversarial attacks, and misuse scenarios. • Support the development of AI governance frameworks, guardrails, and responsible AI security practices. • Drive secure adoption of agentic AI technologies while ensuring compliance with enterprise security and risk requirements. • Contribute to the organization\'s AI security strategy by evaluating evolving threats, technologies, and industry best practices.

Key Responsibilities

Perform security assessments and threat modelling for Agentic AI systems, LLM-powered applications, and autonomous workflows. • Conduct AI Red Team exercises to identify weaknesses in AI agents, models, prompts, tools, and integrated systems. • Develop and implement AI security controls, governance frameworks, and operational guardrails. • Evaluate model security risks including prompt injection, jailbreak attacks, model manipulation, and data leakage scenarios. • Collaborate with AI engineering teams to secure agent orchestration frameworks, APIs, and AI integrations. • Support security monitoring, incident response, and risk mitigation activities for AI-enabled solutions. • Provide expert guidance on secure deployment, operation, and maintenance of enterprise AI platforms.

Skill Requirements

Strong expertise in Agentic AI Security Engineering and AI security architecture principles. • Deep understanding of LLM security, foundation model risks, model hardening, and AI attack vectors. • Experience conducting AI Red Teaming activities, adversarial testing, threat modelling, and security assessments. • Knowledge of AI governance frameworks, responsible AI practices, policy controls, and security guardrails. • Experience working with Security Data Science techniques to identify risks, threats, and anomalous AI behaviors. • Understanding of cloud security, application security, identity management, APIs, and enterprise security architectures. • Strong analytical, communication, stakeholder management, and problem-solving skills in complex environments. ________________________________________ Technical Certification Need to Have and Good to Have Need to Have • CISSP (Certified Information Systems Security Professional) or equivalent cyber security certification. • CCSP (Certified Cloud Security Professional) or equivalent cloud security certification. • Demonstrated experience in AI Security, Cyber Security Engineering, or Security Architecture roles. • Practical knowledge of AI governance, risk management, and secure AI solution delivery. • Experience supporting enterprise AI, machine learning, or cloud-based technology environments. Good to Have • Certified Ethical Hacker (CEH). • Offensive Security Certified Professional (OSCP). • Microsoft Certified: Cybersecurity Architect Expert (SC-100). • Microsoft Azure Security Engineer Associate (AZ-500). • AWS Certified Security Specialty or Google Professional Cloud Security Engineer. • Certifications in Generative AI, Responsible AI, AI Governance, Machine Learning Security, or AI Risk Management. • GIAC certifications related to penetration testing, threat intelligence, cloud security, or security operations.

Other Requirements

Additional Context • This role focuses on securing Agentic AI solutions, autonomous workflows, and advanced LLM-based applications. • Candidates with experience in AI security research, AI threat modelling, and AI governance will be highly preferred. • Knowledge of emerging AI security standards, regulatory requirements, and responsible AI frameworks is advantageous. • Experience working with AI agents, tool-calling architectures, retrieval systems, and multi-agent ecosystems is beneficial. • The role offers an opportunity to shape enterprise AI security capabilities and influence the secure adoption of transformative AI technologies.