Applied AI Engineer, CyberSecurity at Mistral

on-site · full_time · Visa sponsorship

Apply for this role at Mistral

Responsibilities:
- Design and compose red-team and blue-team agentic workflows for real client use-cases (dynamic red-teaming, cloud defense, vulnerability scanning, pen tests).
- Configure and extend cyber harnesses to convert prototypes into reliable, deployable services.
- Translate client security requirements into agentic solutions and ship production-facing features.
- Implement context engineering to provide agents with the right data, prompts and state for cybersecurity tasks.
- Orchestrate multi-agent systems and agent workflows, and integrate with evaluation/benchmarking pipelines.
- Collaborate closely with pentesters, platform engineers, and product teams to iterate on solutions and deliver value to clients.

Requirements:
- 2–5 years experience as an applied AI engineer, machine learning engineer, or similar role with hands-on LLM orchestration.
- Practical experience with RAG, agent frameworks, multi-agent orchestration and context engineering.
- Familiarity with cybersecurity concepts (red/blue teaming, vulnerability scanning, pen testing) or strong aptitude to learn them quickly.
- Proficiency in scripting (Python preferred), containerization, and deploying services in cloud environments.
- Customer-focused mindset with strong communication and problem-solving skills to turn prototypes into production services.
- Comfortable iterating quickly and collaborating across research, security, and product teams.