SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Mistral AI is building full-stack AI solutions—from frontier models to developer tools and applications—partnering with enterprises across finance, manufacturing, defense, healthcare, and the public sector to co-create customized AI systems.
As an Offensive Security Engineer (Pentester), you will safeguard Mistral's AI innovations by proactively hunting vulnerabilities, designing red and purple team exercises, and embedding an attacker's mindset into product development. You'll work at the intersection of offensive security, AI safety, and product development, collaborating with cross-functional teams to harden systems against evolving threats.
Key responsibilities include:
- 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 stress-test defenses and refine detection capabilities
- Partner with defensive teams to translate offensive insights into actionable improvements
- 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 using cutting-edge techniques
- Communicate findings clearly to technical and non-technical stakeholders
- Shape Mistral's security strategy through attacker-informed perspectives on threat modeling and architectural decisions
You bring 7+ years of offensive security experience with a track record of identifying and exploiting vulnerabilities in complex systems. Deep knowledge of AI/ML security risks (prompt injection, data leakage, model manipulation) is essential. Hands-on experience assessing modern tech stacks is required: Kubernetes, cloud-native architectures (AWS/GCP/Azure), CI/CD pipelines, macOS/Linux internals, Python/React applications, and data science toolchains.
You have a builder's mindset—able to write robust tools, automate workflows, and contribute to defensive solutions. Strong intuition for trust boundaries and risk assessment in fast-moving environments. Outstanding communication skills to distill technical nuances into compelling narratives. Collaborative spirit, eager to work alongside engineers, researchers, and product teams.
Ideal candidates have background in AI/data science, experience in high-growth startups or research-driven organizations, or expertise in adjacent disciplines (software engineering, detection engineering, SRE, security architecture).
