AI Security Engineer

What you will do

You will build security into the full AI lifecycle, protecting AI solutions, models, agents, data and integrations. At the same time, you will help apply AI responsibly for detection, analysis, vulnerability management, patch prioritisation and secure development. Human responsibility and control remain the guiding principle.

Your responsibilities include:

• Performing threat modelling, risk and security assessments for GenAI, ML and agentic AI solutions
• Developing guardrails for identity, least privilege, secrets, network isolation, data and prompt security, tool usage, output validation, logging and monitoring
• Testing abuse scenarios, including prompt injection, unwanted data exfiltration, excessive permissions, untrusted output and misuse of tools or agents
• Integrating security requirements into sandboxes, gateways, pipelines, model and dependency management, and production platforms
• Helping design security monitoring and incident response for AI components, including ownership, audit trails and escalation
• Assessing suppliers, models, libraries and external AI services as part of supply chain risk management

What we are looking for

Technical competencies

• Demonstrable experience in cybersecurity engineering, cloud security, application security, IAM, SOC or DevSecOps
• Insight into the specific risks of LLMs, agents, retrieval, and model and data supply chains
• Experience with security testing, technical risk assessments and translating findings into actionable measures
• Ability to enable innovation with proportionate controls, without reducing security to a checklist
• Knowledge of GDPR, AI Act, NIS2 or similar frameworks
• Knowledge of the public sector, G-Cloud or OISZ context is an asset

Generic competencies

• Innovation: you follow the latest trends and experiment with innovative AI technologies
• Problem-solving: you analyse complex issues and translate them into pragmatic solutions
• Collaboration: you work smoothly with colleagues from different disciplines (IT, business, security, architecture)
• Communication: you can explain technical concepts clearly to both technical and non-technical stakeholders
• Advisory skills: you are strong in structuring, visualising, advising and guiding multidisciplinary decision-making
• Results-oriented: you monitor deadlines and ensure quality deliverables

The setting

This assignment runs for 12 months, starting in mid-December 2026. The work location is Brussels, with hybrid working available.

You will need active knowledge of Dutch, English and French.

Selection process

Please include with your application a document of no more than two pages in which you explain your vision on how a Belgian public-sector organisation can deploy artificial intelligence safely and responsibly to create concrete added value for its services and internal operations. Emphasise the technical security of AI solutions and the contribution you can make as an AI Security Engineer to identifying risks and designing, implementing and testing appropriate security measures across the full AI lifecycle.

After receiving CVs, a shortlist of 3 to 5 candidates will be drawn up. These candidates will then be invited for an interview to evaluate their technical and generic competencies as well as their language skills. A ranking will be established afterwards.