CyberSecurity, Offensive Security Engineer

  • Full Time
  • London

Mistral AI

CyberSecurity, Offensive Security Engineer Overview

Company Name Mistral AI
Job Role CyberSecurity, Offensive Security Engineer
Qualifications Not Specified
Category IT Jobs
Job Type Full Time
Location London

At Mistral AI, we are dedicated to harnessing the power of artificial intelligence to streamline tasks, save time, and enhance creativity and learning. Our technology is crafted to seamlessly integrate into everyday work life, democratizing AI through high-performance, optimized, open-source models and solutions. We offer a comprehensive AI platform tailored to meet enterprise needs, whether on-premises or in the cloud. Our dynamic and collaborative team is passionate about AI’s transformative potential, and we are committed to fostering innovation within a diverse workforce spread across France, the USA, the UK, Germany, and Singapore.

As a Security Researcher at Mistral AI, you will play a crucial role in protecting our innovative products, such as Mistral Studio and Mistral Vibe, by anticipating, identifying, and mitigating risks. This position requires an offensive security mindset, focusing on embedding security considerations into our development processes. You will collaborate with cross-functional teams to enhance our systems against evolving threats, ensuring our agents remain resilient and trustworthy.

Key Responsibilities

  • Proactively hunt for vulnerabilities in the interactions between our agentic applications, cloud infrastructure, and foundational models, focusing on realistic and impactful attack vectors.
  • Design and implement red and purple team exercises to simulate advanced adversarial scenarios, testing defenses and enhancing detection capabilities.
  • Collaborate with defensive teams to convert offensive insights into practical improvements, including detection engineering and incident response.
  • Conduct thorough penetration testing across the product suite, which includes AI-driven workflows, custom infrastructure, and user-facing interfaces.
  • Develop and automate offensive tools to maximize impact, utilizing advanced techniques to stay ahead of emerging threats.
  • Clearly communicate findings to both technical and non-technical stakeholders, ensuring they understand risks and prioritize necessary mitigations.
  • Contribute to Mistral AI’s security strategy by providing attacker-informed perspectives during threat modeling, risk assessments, and architectural decisions.

Qualifications

  • A minimum of 7 years of experience in offensive security, with a proven ability to identify and exploit subtle vulnerabilities in complex systems, or equivalent expertise demonstrated through significant achievements.
  • In-depth knowledge of AI and machine learning security risks, including prompt injection, data leakage, model manipulation, and misuse of dynamic UI components.
  • Practical experience with modern technology stacks, including custom Kubernetes deployments, cloud-native architectures (AWS, GCP, or Azure), CI/CD pipelines, and GitHub security best practices.
  • Familiarity with macOS/Linux internals and applications based on Python and React.
  • Experience with data science toolchains and AI/ML infrastructure.
  • A builder’s mindset, capable of writing robust tools, automating offensive workflows, and contributing to defensive solutions within complex codebases.
  • Strong intuition for trust boundaries and risk assessment in fast-paced, high-stakes environments.
  • Excellent communication skills, able to translate technical details into engaging narratives that drive change.
  • A collaborative attitude, willing to work closely with engineers, researchers, and product teams to integrate security into all development phases.

Location and Remote Work

This position is based in one of our European offices, specifically in Paris, France, or London, UK. We will only consider candidates who currently reside in these locations or are willing to relocate. We value in-person collaboration and encourage office attendance at least three days a week to foster relationships and enhance communication. Our remote policy is designed to provide flexibility, improve work-life balance, and boost productivity.

What We Offer

  • Competitive salary and equity options.
  • Health insurance coverage.
  • Transportation allowance.
  • Sports allowance.
  • Meal vouchers.
  • Private pension plan.
  • Generous parental leave policy.
  • Visa sponsorship available.

Degree Requirement: Not Specified

Visa Sponsorship Promising

To apply for this job please visit jobs.lever.co.