AI Security Engineer – LLM & GenAI Security

Pauwels Consulting; Brussel; Hybrid; EUR 70,000 - 95,000; Full time

Job summary

Pauwels Consulting is seeking a specialist to integrate security across the entire AI lifecycle in a prominent public sector organization. The role focuses on protecting AI models, agents, and data while enabling responsible use of innovative technologies for threat detection and secure development.

Responsibilities include threat modeling for GenAI and ML, developing security guardrails for identity, data protection and prompt security, testing for abuse scenarios, and embedding security into

Qualifications

• 3+ years of experience in security engineering including cybersecurity, cloud security, IAM, or DevSecOps.
• 3+ years integrating security controls within software development pipelines and cloud platforms.
• 1+ year identifying security risks for LLMs, agents, and model supply chains.
• 1+ year of security testing and risk assessments.
• Knowledge of GDPR, AI Act, or NIS2 frameworks.
• Proactive, solution-oriented with strong analytical and communication skills.
• Active knowledge of Dutch or French and English.

Responsibilities

• Perform threat modeling, risk assessments, and security evaluations for GenAI, ML, and agentic AI solutions.
• Develop security guardrails for identity management, least privilege, data protection, and prompt security.
• Test for abuse scenarios such as prompt injection, data exfiltration, and unauthorized tool usage.
• Integrate security requirements into sandboxes, gateways, CI/CD pipelines, and production platforms.
• Design security monitoring and incident response protocols specifically for AI components.
• Evaluate the supply chain risk of vendors, models, libraries, and external AI services.

Skills

Cybersecurity

Cloud security

IAM

DevSecOps

SDLC security

Cloud platforms

LLMs risk

Agents risk

Model supply chains

Security testing

GDPR/AI Act/NIS2

Languages EN

Dutch or FR

Job description

Our client, a prominent public sector organization, is seeking a specialist to integrate security across the entire AI lifecycle. This role focuses on protecting AI models, agents, and data while ensuring the responsible application of innovative technologies for threat detection and secure development.

Key responsibilities

• Perform threat modeling, risk assessments, and security evaluations for GenAI, ML, and agentic AI solutions.
• Develop security guardrails for identity management, least privilege, data protection, and prompt security.
• Test for abuse scenarios such as prompt injection, data exfiltration, and unauthorized tool usage.
• Integrate security requirements into sandboxes, gateways, CI/CD pipelines, and production platforms.
• Design security monitoring and incident response protocols specifically for AI components.
• Evaluate the supply chain risk of vendors, models, libraries, and external AI services.

Requirements

• You have 3+ years of experience in security engineering covering cybersecurity, cloud security, IAM, or DevSecOps.
• You possess 3+ years of experience integrating security controls within software development pipelines and cloud platforms.
• You bring 1+ years of experience identifying security risks associated with LLMs, agents, and model supply chains.
• You have 1+ years of experience conducting technical security testing and risk assessments.
• You possess 1+ years of knowledge regarding GDPR, AI Act, or NIS2 frameworks.
• You're proactive and solution-oriented with strong analytical and communication skills.
• You have active knowledge of Dutch OR French (with good understanding of the other language), and English.

Nice to Haves

• Experience within the public sector or the G-Cloud environment.
• Ability to translate technical findings into actionable measures for non-technical stakeholders.

Details

• Start date: 14/12/2026
• Duration: 12 months
• Work regime: Full-time
• Location: Brussels
• Working model: Hybrid with partial remote work
• Contract: open to both permanent employees and freelancers