AI Security Engineer (K10226)

About the Position

We are seeking an AI Security Engineer (K10226) to protect AI solutions, models, agents, data, and integrations, ensuring responsible AI application for detection, analysis, vulnerability management, patch prioritization, and secure development.

Responsibilities

• Threat modeling, 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 rights, unreliable 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 vendors, models, libraries, and external AI services as part of the chain risk.

Requirements

• Core Skills

  • AI-security risks: LLM’s, agents, retrieval, and model and data supply chains.
  • Experience integrating security measures in software development and cloud platforms.
  • Security engineering: cybersecurity, cloud, applications, IAM, SOC, or DevSecOps.
  • Translating security testing and technical risk assessments into actionable measures.

• Languages

  • English: Active knowledge
  • Dutch: Active knowledge
  • French: Active knowledge

Nice to Have

• Knowledge of GDPR, AI Act, NIS2, or similar frameworks.
• Knowledge of the public sector, G-Cloud, or OISZ context is a plus.

We Offer

• Opportunity to work in Brussels with the possibility of part-time remote work.

About the Company

Join our team and contribute to the secure and responsible deployment of artificial intelligence to create concrete added value for pension services and internal operations. Emphasize the technical security of AI solutions and the contribution you can make as an AI Security Engineer in identifying risks and designing, implementing, and testing appropriate security measures throughout the AI lifecycle.

Application Process

Submit a document of up to 2 pages outlining your vision on how the Federal Pension Service can safely and responsibly deploy artificial intelligence to create concrete added value for its pension services and internal operations. Emphasize the technical security of AI solutions and the contribution you can make as an AI Security Engineer in identifying risks and designing, implementing, and testing appropriate security measures throughout the AI lifecycle.

After receiving the CVs, they will be analyzed, and a shortlist of 3-5 candidates will be established based on the criteria set in the ProUnity contract. These candidates will be invited for an interview where their technical and generic competencies, as well as their language skills, will be evaluated. A ranking will then be established.