Agentic AI Security Specialist - Inside IR35 - Hybrid

Key Responsibilities

• Provide specialist security expertise across Agentic AI and LLM-based solutions.
• Assess and address security risks associated with AI models and AI-enabled systems.
• Support LLM and model security activities throughout the delivery life cycle.
• Perform and contribute to AI red teaming to identify weaknesses, attack paths and security risks.
• Support the definition and implementation of AI governance, security guardrails and controls.
• Apply security data science techniques to help identify, assess and manage AI-related security risks.
• Work closely with client stakeholders, technology teams and security teams to provide clear and credible security guidance.
• Collaborate effectively across cross-functional and geographically dispersed teams.
• Apply strong problem-solving skills to resolve complex security challenges and support continuous improvement.

Key Requirements

• Strong experience in Agentic AI security engineering.
• Strong knowledge of LLM security and model security.
• Experience of AI red teaming.
• Knowledge of AI governance and guardrails.
• Experience or strong knowledge of security data science.
• Excellent stakeholder management and client-facing skills, with the ability to build strong professional relationships.
• Strong team player with experience working across cross-functional and geographically dispersed teams.
• Strong problem-solving and conflict-resolution capabilities.
• High level of professionalism, integrity and accountability.
• Adaptable and resilient, with a customer-focused mindset and commitment to continuous improvement.

Duration: 12 Months

Location: Hybrid - 3 days per week in the office

Start Date: 01/11/2026

Positions: 2