Senior HPC System Administrator

Overview

the company | Senior HPC System Administrator | Richmond, BC, Canada | ONSITE or HYBRID (3 days/week) | Full-Time | $126k-$154k CAD | Immigration support for US candidates

the company is a fusion energy startup (est. 2002) operating a fusion demonstration machine (LM26) at our Richmond, BC labs. We're hiring an HPC Admin to manage and evolve our Rocky Linux cluster (70 nodes, 1PB storage, SLURM) and help shape our broader research data infrastructure, bridging simulation and experimental data systems.

Lead and maintain the company’s Rocky Linux HPC cluster, ensuring high availability and optimal performance across 70 nodes and 1PB of storage. Configure, monitor, and tune SLURM workload management, Infini Band networking, and container runtime (Apptainer). Design and evolve data pipelines using HDF5, Parquet, DVC, LakeFS, Click House, DuckDB, and MongoDB. Implement and manage observability stack with Prometheus and Grafana. Collaborate with research teams to integrate simulation and experimental data systems.

• 5+ years of experience in scientific/HPC computing.
• 2+ years managing HPC clusters.
• Strong Linux system administration background (Rocky Linux).
• Experience with SLURM, Infini Band, Apptainer, Prometheus/Grafana, HDF5/Parquet, DVC/LakeFS, Click House/DuckDB, MongoDB.