Requirements

Operating system

Windows

Our requirements

• 5+ years of experience in HPC environments, with deep knowledge of SLURM, MPI, and Linux-based system management.
• Proven expertise in cloud migration of HPC clusters, ideally within GCP.
• Strong scripting and automation skills in Python and Bash, plus tools like Ansible and Terraform.
• Experience with Spack for software stack management in HPC.
• Deep understanding of GCP services: Compute Engine, Cloud Storage, VPC, IAM.
• Strong analytical skills for performance tuning and job scheduling in complex HPC setups.
• Proficiency in English (C1/C2) is required for communication across distributed, international teams.
• Ability to operate in cross-functional, multi-vendor environments and present technical solutions clearly.

Optional

• GCP Professional DevOps Engineer certification (or equivalent).
• Familiarity with GCP-specific HPC features: Preemptible VMs, HPC VM images, autoscaling strategies.
• Experience with profiling/debugging HPC workloads, including performance optimization tools.
• Understanding of HPC data management, parallel file systems, and high-throughput data transfer.
• Knowledge of container solutions in HPC contexts (e.g., Singularity, Docker).
• Familiarity with Spark, Hadoop, or Big Data frameworks in HPC environments.

Your responsibilities

• Lead the end-to-end migration of SLURM-based HPC clusters from on-premises infrastructure to Google Cloud Platform (GCP).
• Design, deploy, and manage secure and scalable HPC infrastructure in GCP.
• Optimize SLURM configurations and job workflows to improve efficiency and cloud resource utilization.
• Automate cluster lifecycle processes (deployment, configuration, maintenance) using Python, Bash, Ansible, and Terraform.
• Manage HPC software stacks with Spack to streamline the deployment of libraries and tools.
• Troubleshoot and support MPI, OpenMP, and other HPC applications on GCP-based clusters.
• Collaborate closely with engineering, operations, and business teams to ensure continuity and performance.
• Conduct performance tuning, resource optimization, and monitor cost-efficiency across workloads.
• Stay current with GCP HPC innovations, including VM types, networking, and autoscaling strategies.