Govern & secure
Work mode: HybridAI Security Engineer
You keep AI deployments safe. You red-team the systems Code75 builds, secure the data pipelines and access around them, and design the controls that contain prompt injection, data leakage and misuse before they reach production.
What you’ll do
- Red-team AI applications: prompt injection, data exfiltration and abuse.
- Design least-privilege access and guardrails for agents and tools.
- Secure data pipelines and the boundaries between trusted and untrusted content.
- Define monitoring and response for AI-specific threats.
What we look for
- A security background: application, cloud or offensive security.
- Understanding of LLM-specific risks and the OWASP Top 10 for LLM applications.
- Hands-on testing skill and a constructive, fix-oriented mindset.
- The ability to explain risk to non-security stakeholders.
Nice to have
- Experience testing LLM or agentic systems.
- Professional French and English.
Apply for this role
Send your CV and a short note on why this role fits. You will hear back from a person, not a tracker.
Other roles in this team
Work on AI that ships
Real client systems in production, not demos. If that is the work you want, we should talk.