Offensive Security Engineer

About the Role

Join Mistral AI as an Offensive Security Engineer to safeguard our cutting-edge AI products by anticipating and mitigating security risks from an attacker's perspective.

Responsibilities

• Proactively hunt for vulnerabilities in agentic applications, cloud infrastructure, and foundational models.
• Design and execute red and purple team exercises to test defenses.
• Partner with defensive teams to translate offensive insights into actionable improvements.
• Conduct in-depth penetration testing across the product suite.
• Build and automate offensive tooling to scale impact.
• Communicate findings clearly to technical and non-technical stakeholders.
• Shape security strategy with attacker-informed perspectives.

Requirements

• 7+ years of offensive security experience or equivalent expertise.
• Deep knowledge of AI/ML security risks (prompt injection, data leakage, model manipulation).
• Hands-on experience with Kubernetes, containerized environments, cloud-native architectures (AWS, GCP, Azure), CI/CD pipelines, macOS/Linux internals, Python, and React.
• Experience with data science toolchains and AI/ML infrastructure.
• Ability to write robust tools and automate offensive workflows.
• Strong intuition for trust boundaries and risk assessment.
• Outstanding communication and collaboration skills.

Nice-to-Haves

• Background in AI, data science, or related fields.
• Experience in high-growth startups or research-driven organizations.
• Expertise in software engineering, detection engineering, SRE, or security architecture.