Staff AI Security Engineer (AI)

Location: Hybrid in The Hague, Belgium, or Berlin

Company

hirify.global develops cybersecurity capabilities for customer environments, with a research and innovation function focused on problems ahead of MDR, incident response, and threat hunting.

What you will do

• Expand Agentic SOC capabilities by identifying investigation, triage, and response workflows that can be improved with AI.
• Prototype and evaluate agentic systems for vulnerability identification, exposure validation, exploitability assessment, detection logic, and prioritization.
• Turn successful research prototypes into customer-facing tools, agentic skills, browser extensions, and production capabilities.
• Assess agentic, LLM, and RAG systems for prompt injection, unsafe tool use, data leakage, and supply-chain risks.
• Work with SecOps, engineering, research, and security teams to implement mitigations and understand operational AI-related threats.
• Write technical research, publish valuable tooling, represent hirify.global externally, and track OWASP, NIST, and ENISA guidance.

Requirements

• Strong hands-on cybersecurity experience in areas such as SOC operations, incident response, threat detection, vulnerability research, offensive security, or security engineering.
• Staff-level technical judgment, including independently selecting valuable research questions, building prototypes, and influencing technical teams without formal authority.
• Hands-on experience with LLMs, agents, RAG, or related AI systems through professional work, research, open-source contributions, or substantial personal projects.
• Working proficiency in English required. Dutch or German is a plus, not a requirement.
• Ability to write and execute a 100-day plan and deliver an Agentic SOC or AI-driven CVE-hunting prototype with measurable operational impact.
• Ability to assess at least one production AI system and help establish practical AI security review controls.

Nice to have

• Offensive security experience in pentesting, red teaming, or vulnerability research applied to AI and LLM systems.
• Background in SOC operations, MDR, or incident response.
• AI security community contributions, including CTF write-ups, jailbreaks, mitigations, OWASP LLM Top 10 or MITRE ATLAS involvement, and conference talks.
• Experience with managed LLM platforms such as Bedrock.

Culture & Benefits

• Significant freedom to explore and build, with real technical ownership of AI security practices.
• Direct path from research findings to shipped mitigations and customer-facing capabilities.
• Collaboration with security specialists, engineers, researchers, and colleagues with hands-on AI expertise.
• Quarterly get-togethers and an annual company-wide retreat.
• Generous time off, including a volunteering day and dedicated wellbeing time off.