Senior AI Security Architect

Position Overview

We are searching for an experienced Senior AI Security Architect to spearhead the System Security Architecture and Threat Modeling for safeguarding autonomous AI systems. The role involves ensuring these systems operate securely, with full auditability and privacy protection across multiple platforms.

Required Qualifications and Expertise

• Bachelor's degree in Computer Science, Computer Engineering, Statistics, Applied Mathematics, Data Science or Analytics.
• Minimum 6 years of professional experience in cybersecurity, including 2 to 3 years specializing in AI/ML or large language model (LLM) security.
• Proven hands-on skills securing cloud-native infrastructures such as serverless environments, APIs, and databases.
• Strong knowledge of agentic AI systems and securing API-based automation.
• In-depth understanding of large language model risks including prompt injection, data leakage, and Retrieval-Augmented Generation (RAG) security considerations.
• Experience conducting threat modeling and designing secure AI workflow systems.
• Proficiency in identity and access control mechanisms and policy-based authorization frameworks such as Attribute-Based Access Control (ABAC).
• Expertise in audit logging mechanisms providing traceability and reproducibility within AI ecosystems.
• Familiar with data governance policies and privacy controls in sensitive data environments.
• Good grasp of industry standard AI security frameworks, specifically the Model AI Governance Framework.
• Experience applying security testing, vulnerability analysis, and adversarial testing methodologies.
• Excellent written, verbal, and presentation communication skills.

Preferred Skills

• Hands-on experience with Policy-as-Code or logic-based authorization systems.
• Knowledge of immutable logging, digital forensics, and designing tamper-evident audit trails.

Key Responsibilities

• Lead the design of security architecture for autonomous AI systems, establishing controls to block unauthorized operations.
• Carry out detailed threat modeling to identify AI-specific risks such as prompt injections and improper AI agent use.
• Develop human-in-the-loop safety controls for sensitive AI decision points.
• Create comprehensive audit trails documenting AI outputs, data usage, and model versions to ensure traceability.
• Guarantee reproducibility and explainability of AI decisions for compliance and auditing purposes.
• Enforce strong data governance principles and least privilege access across diverse inter-agency data integrations.
• Conduct proactive security evaluations including vulnerability assessments and adversarial scenario simulations of AI workflows.
• Implement advanced privacy measures to safeguard sensitive commercial and governmental information.
• Collaborate closely with AI engineering and product development teams within an agile environment balancing rapid innovation and security.
• Translate complex AI security risks into understandable and actionable recommendations for senior leadership.

Additional Information

Applicants consent to the collection and use of their personal data for recruitment purposes in line with the company's privacy policy. Confidentiality will be maintained and only shortlisted candidates will be contacted for interviews. Employment Agency Licence No. 07C5639.