Mistral AI · Paris
Data & AISolutionsFullTimeposted 2mo ago
Mistral provides full-stack AI solutions: from frontier models to developer tools, applications, and compute. We partner with enterprises tackling the hardest problems—across high-stakes industries like finance, manufacturing, defense, healthcare, and the public sector—co-creating customized AI systems that they can run on their terms.
We are a dynamic, collaborative team passionate about AI and its potential to transform society. Our diverse workforce thrives in competitive environments and is committed to driving innovation. Our teams are distributed between Europe, North America, Asia and the Middle East. We are creative, low-ego and team-spirited.
Role summary
We are seeking an Applied AI Engineer to build the customer-facing cyber service and use-cases on top of our cyber harnesses. You will turn "we have agents" into "we shipped something a client uses." This role is about composing red-team/blue-team agentic workflows, configuring harnesses for real-world scenarios, and delivering value directly to clients.
Your work will bridge the gap between our foundational cyber harnesses and the agentic solutions that clients deploy. While SWE-Cyber makes the platform robust and scalable, and Pentesters run the solution and guide the direction, you will focus on building the agentic use-cases and client-facing service that solve real security problems.
What you will do
Client-Facing Agentic Solutions
• Compose red-team / blue-team agentic workflows for production use-cases
• Configure harnesses for cloud defense, vulnerability scanning, dynamic red-teaming, and penetration testing scenarios
• Work directly on client use-cases, translating security requirements into agentic solutions
• Turn prototype agents into deployed services that clients rely on
Context Engineering & Orchestration
• Design and implement context engineering that enables agents to operate effectively in cybersecurity domains
• Orchestrate multi-agent systems for complex security workflows
• Build the agentic layer that sits between the harness and the client
Service Delivery
• Ship fast and iterate based on client feedback and real-world performance
• Operate independently while leveraging internal building blocks and frameworks
• Collaborate with pentesters to ensure domain accuracy and effectiveness
• Partner with SWE-Cyber to ensure the platform supports your use-case requirements
About you
• Strong applied AI engineer with hands-on experience building agents, LLM orchestration, context engineering, evals, and RAG systems
• You ship fast, with a bias toward action and delivery
• Operate independently with a customer-led mindset
• Able to reuse internal components and bricks effectively
• Some cyber context is a real plus, but not mandatory - we can pair you with pentesters for domain depth
• Strong problem-solving abilities and attention to detail
• Excellent communication skills and collaborative attitude
It would be ideal if you also have:
• Genuine cyber or pentest knowledge
• Experience building agentic harnesses or multi-agent systems end-to-end
• Strong background in evals and benchmarking of agent systems
• Experience with security tooling or workflows
• Prior work on production AI systems in regulated or high-stakes environments
We offer a comprehensive benefits package designed to support your well-being, growth, and work-life balance. Benefits vary by country and may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, meal and transportation allowances, and other location-specific perks.
For the most up-to-date details on benefits available in your location, please refer to our Benefits page.
Your privacy matters to us. You can learn more about how we handle your personal data in our Applicant Privacy Policy.