Applied AI Engineer, CyberSecurity
Remote • Paris • Full-time
Posted 1mo ago
Job Location
Paris
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
Applied AI Engineer
About the job
Mistral AI is seeking an Applied AI Engineer to build customer-facing cyber services and use-cases on top of our cyber harnesses. This role focuses on composing red-team/blue-team agentic workflows, configuring harnesses for real-world scenarios, and delivering value directly to clients. You will bridge the gap between our foundational cyber harnesses and the agentic solutions that clients deploy, focusing on building agentic use-cases and client-facing services that solve real security problems.
Responsibilities
- 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.
- 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.
- 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.
Requirements
- Strong applied AI engineer with hands-on experience building agents, LLM orchestration, context engineering, evals, and RAG systems.
- Bias toward action and delivery.
- Operate independently with a customer-led mindset.
- Able to reuse internal components and bricks effectively.
- Strong problem-solving abilities and attention to detail.
- Excellent communication skills and collaborative attitude.
- Genuine cyber or pentest knowledge (ideal).
- Experience building agentic harnesses or multi-agent systems end-to-end (ideal).
- Strong background in evals and benchmarking of agent systems (ideal).
- Experience with security tooling or workflows (ideal).
- Prior work on production AI systems in regulated or high-stakes environments (ideal).