CyberSecurity, Offensive Security Engineer

About the Role

Mistral AI is seeking an Offensive Security Engineer to secure its AI products and infrastructure. In this pentesting and red team role, you'll identify vulnerabilities across agentic applications, cloud systems, and foundational models—then work with defensive teams to translate those findings into measurable security improvements. Your work will directly shape how Mistral hardens its systems against sophisticated threats.

Responsibilities

• Conduct vulnerability hunting and penetration testing across AI-driven applications, cloud infrastructure, and product interfaces, focusing on realistic attack vectors.
• Design and execute red team and purple team exercises to stress-test defenses, simulate adversarial scenarios, and refine detection capabilities.
• Build and automate offensive security tools to scale impact and stay ahead of emerging threats.
• Partner with defensive and engineering teams to translate offensive findings into actionable detection improvements and architectural recommendations.
• Perform threat modeling and risk assessment to inform security strategy and product design decisions.
• Communicate technical findings clearly to both technical and non-technical stakeholders, ensuring priorities align on risk mitigation.

Requirements

• 7+ years of offensive security experience with a demonstrated track record of identifying vulnerabilities in complex systems, or equivalent exceptional achievements.
• Deep knowledge of AI/ML security risks, including prompt injection, data leakage, model manipulation, and abuse of dynamic UI components.
• Hands-on experience assessing modern technology stacks:
  • Kubernetes deployments and containerized environments
  • Cloud-native architectures (AWS, GCP, or Azure)
  • CI/CD pipelines and GitHub security best practices
  • macOS/Linux internals and Python/React-based applications
  • Data science toolchains and AI/ML infrastructure
• Ability to write and automate offensive tools, contribute to defensive solutions, and navigate complex codebases.
• Strong intuition for trust boundaries and risk assessment in fast-moving environments.
• Excellent communication skills with the ability to translate technical nuances into compelling narratives that drive change.
• Collaborative mindset, eager to embed security across engineering, research, and product teams.

Ideal Background

• Experience in AI, data science, or related fields, with understanding of how security intersects with model behavior and system design.
• Background in high-growth startups or research-driven organizations prioritizing agility and innovation.
• Expertise in adjacent disciplines such as software engineering, detection engineering, SRE, or security architecture.

Benefits

Mistral AI offers a comprehensive benefits package that varies by location and may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, meal and transportation allowances, and other location-specific perks. For current details on benefits available in Paris, refer to Mistral's Benefits page.