AI Security Engineer: Guardrails & Secure AI Lifecycle

Neurho Solutions; Brussel; Sur place; EUR 85 000 - 115 000; Plein temps

Résumé du poste

Neurho Solutions is seeking an AI Security Engineer to embed security into the full AI lifecycle, protecting models, data and integrations while promoting responsible AI use in security operations and development.

You will work on threat modelling, guardrail design, testing and incident response across GenAI, ML and agentic AI solutions, with a focus on GDPR, the AI Act and cloud security practices. Collaborative, cross-functional work is expected across IT and security teams.

Qualifications

• Experience in AI security risks across LLMs, agents, retrieval and model/data supply chains.
• Experience integrating security controls into software development.
• Experience integrating security controls into cloud platforms.
• Experience with GDPR, the AI Act, NIS2 or comparable frameworks.
• Experience in cybersecurity engineering, cloud security, application security, IAM, SOC or DevSecOps.
• Experience translating technical security risk assessments into actionable measures.

Responsabilités

• Carry out threat modelling and security risk assessments for GenAI, ML and agentic AI solutions.
• Design guardrails for access, secrets, network isolation, data and prompts, tool use, output validation, logging and monitoring.
• Test scenarios such as prompt injection, data exfiltration, excessive privileges and misuse of agents or tools.
• Integrate security requirements into sandboxes, gateways, pipelines, model and dependency management, and production platforms.
• Help design monitoring and incident response for AI components, including ownership, audit trails and escalation.
• Assess suppliers, models, libraries and external AI services for supply-chain risks.

Connaissances

Threat modelling

Security in AI lifecycle

Cloud security

DevSecOps

GDPR / AI Act compliance

Security testing

Security risk assessments

Incident response

Stakeholder communication

Audit trails

Data protection

Access control

Prompt injection testing

Description du poste

Neurho Solutions is seeking an AI Security Engineer to embed security into the full AI lifecycle, protecting models, data and integrations while promoting responsible AI use in security operations and development.

You will work on threat modelling, guardrail design, testing and incident response across GenAI, ML and agentic AI solutions, with a focus on GDPR, the AI Act and cloud security practices. Collaborative, cross-functional work is expected across IT and security teams.