CyberSecurity Engineer, Offensive Security
Remote • Paris • Full-time
Posted 4mo ago
About the job
Mistral AI is a pioneering company at the forefront of AI innovation, developing cutting-edge models, products, and solutions that democratize AI. We are building products like Mistral Studio and Mistral Vibe that redefine user interaction with AI. Our mission is to integrate AI seamlessly into daily life, enhancing learning, creativity, and efficiency. We are a dynamic, collaborative, and diverse team passionate about AI's potential to transform society, with a global presence across France, the USA, the UK, Germany, and Singapore. We are seeking a Security Researcher to safeguard our innovations by anticipating, identifying, and mitigating risks, embedding an attacker's mindset into our product development.
Responsibilities
- Proactively hunt for vulnerabilities in agentic applications, cloud infrastructure, and foundational models, focusing on realistic, high-impact attack vectors.
- Design and execute red and purple team exercises to simulate adversarial scenarios and test defenses.
- Partner with defensive teams to translate offensive insights into actionable improvements for detection and incident response.
- Conduct in-depth penetration testing across the product suite, including AI-driven workflows, custom infrastructure, and user-facing interfaces.
- Build and automate offensive tooling to scale impact and stay ahead of emerging threats.
- Communicate findings clearly to technical and non-technical stakeholders to ensure risks are understood and mitigations are prioritized.
- Shape Mistral AI’s security strategy by contributing attacker-informed perspectives to threat modeling, risk assessment, and architectural decisions.
Requirements
- 7+ years of offensive security experience, or equivalent expertise demonstrated through exceptional achievements.
- Deep knowledge of AI/ML security risks, including prompt injection, data leakage, model manipulation, and abuses of dynamic UI components.
- Hands-on experience assessing modern technology stacks such as custom Kubernetes deployments, containerized environments, cloud-native architectures (AWS, GCP, or Azure), CI/CD pipelines, GitHub security best practices, macOS/Linux internals, Python/React-based applications, and data science toolchains.
- A builder’s mindset with the ability to write robust tools, automate offensive workflows, and contribute to defensive solutions.
- Strong intuition for trust boundaries and risk assessment in fast-moving, high-stakes environments.
- Outstanding communication skills to distill technical nuances into compelling narratives.
- A collaborative spirit, eager to work alongside engineers, researchers, and product teams.