AI Security Engineer - Secure GenAI Lifecycle On-Site

Keystone Solutions; Brussel Hoofdstad; On-site; EUR 75,000 - 110,000; Full time

Job summary

Keystone Solutions is seeking an AI Security Engineer for a client-site consultancy focused on securing AI solutions across the lifecycle. You will protect models, data, agents and integrations while ensuring responsible AI application, covering detection, risk assessment, patch prioritization and secure development.

Responsibilities include threat modeling for GenAI and ML, building guardrails for identity, data, prompts and logging, testing abuse scenarios, and ensuring secure production

Qualifications

• Experience in cybersecurity engineering, cloud security, IAM, SOC or DevSecOps.
• Understanding of risks related to LLMs, agents, retrieval and data supply chains.
• Experience with security testing and technical risk assessments.
• Ability to balance innovation with proportional security controls.
• Knowledge of GDPR, AI Act, NIS2 or similar frameworks.

Responsibilities

• Conduct threat modeling, 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, unreliable output, and misuse of tools or agents.
• Integrate security requirements into sandboxes, gateways, pipelines, model and dependency management, and production platforms.
• Assist in designing security monitoring and incident response for AI components, including ownership, audit trails, and escalation.
• Evaluate vendors, models, libraries, and external AI services as part of supply chain risk.

Skills

Cybersecurity engineering

Cloud security

IAM

SOC

DevSecOps

Security testing

Regulatory knowledge

Job description

Keystone Solutions is seeking an AI Security Engineer for a client-site consultancy focused on securing AI solutions across the lifecycle. You will protect models, data, agents and integrations while ensuring responsible AI application, covering detection, risk assessment, patch prioritization and secure development.

Responsibilities include threat modeling for GenAI and ML, building guardrails for identity, data, prompts and logging, testing abuse scenarios, and ensuring secure production