Senior Offensive Security Engineer: AI & Cloud Defense

Mistral; Paris; Hybride; EUR 90 000 - 120 000; Plein temps

Résumé du poste

Mistral AI is seeking a Security Researcher to help safeguard our agentic AI products, including Mistral Studio and Mistral Vibe. You will anticipate, identify, and mitigate risks by embedding an attacker’s mindset into development, security reviews, and product design.

You’ll lead offensive security efforts across cloud infrastructure, AI/ML systems, and user interfaces, performing red/purple team exercises, penetration testing, and tooling development, while collaborating with engineers and

Qualifications

• 7+ years of offensive security experience and vulnerability research.
• Strong knowledge of AI/ML security risks and threat vectors.
• Experience with Kubernetes, cloud platforms, CI/CD and secure software supply chains.
• Excellent communication and collaboration across cross-functional teams.

Responsabilités

• Proactively hunt vulnerabilities in agentic apps, cloud infra, and model interactions.
• Design and run red and purple team exercises to test defenses.
• Translate offensive insights into actionable improvements for detection and response.
• Perform in-depth penetration testing across product suite including AI workflows.
• 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.

Connaissances

Offensive security

AI/ML security

Threat modeling

Communicator

Collaboration

Outils

Kubernetes

Docker

AWS / GCP / Azure

GitHub security

Python

React

Description du poste

Mistral AI is seeking a Security Researcher to help safeguard our agentic AI products, including Mistral Studio and Mistral Vibe. You will anticipate, identify, and mitigate risks by embedding an attacker’s mindset into development, security reviews, and product design.

You’ll lead offensive security efforts across cloud infrastructure, AI/ML systems, and user interfaces, performing red/purple team exercises, penetration testing, and tooling development, while collaborating with engineers and