Senior Offensive Security Engineer — AI/ML Security

Mistral.ai; Paris; Hybride; EUR 110 000 - 150 000; Plein temps

Résumé du poste

Mistral AI is seeking an Offensive Security Pentester to safeguard our agentic AI products by anticipating and mitigating risks before they materialize. You will hunt for vulnerabilities in the interactions between applications, cloud infrastructure, and foundational models, shaping threat modeling and architectural decisions.

You’ll work with cross-functional teams to harden our systems, design red/purple team exercises, automate tooling, and translate findings into concrete defenses to keep

Qualifications

• 7+ years of offensive security experience or equivalent achievements.
• Deep knowledge of AI/ML security risks (prompt injection, data leakage, model manipulation).
• Hands-on experience with modern tech stacks (Kubernetes, cloud, CI/CD, GitHub security).
• Experience with Python/React-based applications and macOS/Linux internals.
• Builder’s mindset: write robust tools and automate workflows.
• Strong intuition for trust boundaries and risk in fast-moving environments.
• Outstanding communication to distill complex topics for diverse stakeholders.

Responsabilités

• Proactively hunt for vulnerabilities in agentic applications, cloud infra, and models.
• Design and execute red and purple team exercises to stress-test defenses.
• Translate offensive insights into actionable improvements across detection and incident response.
• Conduct in-depth penetration testing across product suites (AI-driven workflows, infra, UIs).
• Build and automate offensive tooling to scale impact.
• Communicate findings clearly to technical and non-technical stakeholders.
• Contribute attacker-informed perspectives to threat modeling and architecture decisions.

Connaissances

Offensive security

AI/ML security

Communication

Collaboration

Threat modeling

Outils

Kubernetes

Cloud platforms

CI/CD security

Python

React

Data science tooling

Description du poste

Mistral AI is seeking an Offensive Security Pentester to safeguard our agentic AI products by anticipating and mitigating risks before they materialize. You will hunt for vulnerabilities in the interactions between applications, cloud infrastructure, and foundational models, shaping threat modeling and architectural decisions.

You’ll work with cross-functional teams to harden our systems, design red/purple team exercises, automate tooling, and translate findings into concrete defenses to keep