AI Security Engineer – GenAI Security & Guardrails

HumanInTech; Brussel Hoofdstad; Hybride; EUR 55 000 - 90 000; Plein temps

Résumé du poste

HumanInTech in Brussels is seeking a Cybersecurity Engineer to embed security across the AI lifecycle, protecting models, data and integrations and applying responsible AI principles.

You will perform threat modelling, risk and security assessments for GenAI, ML and agentic AI solutions, and develop guardrails for identity, data, and prompt security. This 12-month assignment welcomes freelancers or employees.

Qualifications

• Demonstrable experience in cybersecurity engineering, cloud security, or application security.
• Knowledge of GDPR, AI Act, NIS2 or similar frameworks.
• Experience with security testing and translating findings into actionable measures.

Responsabilités

• Perform threat modelling, risk 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 and misuse of tools or agents.
• Integrate security requirements into sandboxes, gateways, pipelines, model and dependency management, and production platforms.
• Help design security monitoring and incident response for AI components, including audit trails and escalation.
• Assess suppliers, models, libraries and external AI services as part of supply chain risk management.

Connaissances

Cybersecurity engineering

Cloud security

Application security

IAM

DevSecOps

Threat modelling

Security testing

Risk assessments

GDPR / AI Act / NIS2

LLM / AI security

Communication

Formation

Bachelor's degree or higher

Description du poste

HumanInTech in Brussels is seeking a Cybersecurity Engineer to embed security across the AI lifecycle, protecting models, data and integrations and applying responsible AI principles.

You will perform threat modelling, risk and security assessments for GenAI, ML and agentic AI solutions, and develop guardrails for identity, data, and prompt security. This 12-month assignment welcomes freelancers or employees.