About the job

Mistral AI is building one of Europe’s largest AI infrastructures to deliver private, integrated stacks for customers—from bare-metal servers to fully managed platforms. As a DevOps Engineer on the HPC Services team, you will design and maintain scalable, highly available, and fault-tolerant infrastructures that support both internal operations and customer platforms. Your responsibilities include automating the lifecycle of compute nodes, developing tools for reliability and performance improvements, driving CI/CD, managing container orchestration (e.g., Kubernetes), and contributing to monitoring, logging, and alerting systems. You'll work closely with the R&D and security teams to ensure robust and compliant systems across multiple HPC clusters. The role demands 7+ years of experience in DevOps or SRE roles, proficiency in scripting (Python, Go, Bash), strong skills in Kubernetes, CI/CD, Terraform, and observability tools, along with a deep understanding of distributed systems, networking, and security. Ideal candidates also have experience with Slurm and distributed storage like Lustre or Ceph. While the role is remote-friendly, onboarding in Paris for the first month is required, and visa sponsorship is available.