AI Security Engineer (AI)

Location: Brussels, Belgium; on-site consultancy work at a client site.

Company

hirify.global delivers consultancy projects across different client environments, with an emphasis on on-site engagements and consultant development.

What you will do

• Conduct threat modeling, risk assessments, and security assessments for GenAI, ML, and agentic AI solutions.
• Develop guardrails for identity, least privilege, secrets, network isolation, data and prompt security, tool usage, output validation, logging, and monitoring.
• Test abuse scenarios including prompt injection, data exfiltration, excessive permissions, unreliable outputs, and misuse of tools or agents.
• Integrate security requirements into sandboxes, gateways, pipelines, model and dependency management, and production platforms.
• Design security monitoring and incident response for AI components, including ownership, audit trails, and escalation.
• Evaluate vendors, models, libraries, and external AI services for supply-chain risk.

Requirements

• Proven experience in cybersecurity engineering, cloud security, application security, IAM, SOC, or DevSecOps.
• Understanding of risks related to LLMs, agents, retrieval, and model and data supply chains.
• Experience with security testing and technical risk assessments, translating findings into actionable measures.
• Experience integrating security measures into software development and cloud platforms.
• Knowledge of GDPR, AI Act, NIS2, or comparable frameworks.
• Ability to enable innovation through proportional controls and pragmatic security solutions.
• Active knowledge of Dutch, English, and French is required.

Nice to have

• Familiarity with the public sector, G-Cloud, or OISZ context.

Culture & Benefits

• Dynamic consultancy projects with varied challenges across client environments.
• On-site work supporting growth as a consultant and intensive learning through client engagements.
• Career growth within the hirify.global framework.
• Full-time engagement for 12 months, from 14 December 2026 to 13 December 2027.

Hiring process

• Attach a document of no more than two pages outlining a safe and responsible AI deployment vision for the Federal Pension Service, with emphasis on technical security and lifecycle risk management.
• CVs will be reviewed against ProUnity contract criteria; a shortlist of 3–5 candidates will be invited to an interview assessing technical competencies, generic competencies, and language skills, followed by ranking.