High-Performance Computing (HPC) Administrator

High-Performance Computing (HPC) AdministratorSouth Houston, TX – Hybrid 2-3 days per week Contract-to-hirePay rate around $64/hr, depending on experiencePOSITION SUMMARY:The High-Performance Computing (HPC) Systems Administrator is responsible for maintaining, supporting, and optimizing the software environment and daily operational stability of the client’s research computing cluster. This includes ensuring access and uptime across head nodes, compute nodes, development nodes, and GPU nodes within a Linux-based ecosystem that utilizes the Slurm Workload Manager. The role focuses on environment configuration, user support, software installation, workflow onboarding, and coordination with central IT teams for networking and storage—specifically Tier 1 PixStor and Tier 2 Isilon.POSITION KEY ACCOUNTABILITIES:Administers and maintains a scientific research Linux-based HPC environment with both compute and GPU nodes.Installs, updates, and manages scientific software, libraries, toolchains, and environment modules.Oversees Slurm job scheduling, queue configuration, and workload performance.Ensures overall cluster uptime, accessibility, stability, and operational continuity.Utilizes monitoring tools to assess system health and address operational issues.Coordinates with storage teams to ensure reliable access to multi-level storage systems.Supports data access, permissions, and data movement best practices for researchers.Assists users in porting and optimizing computational workflows. Languages include Bash, R, Python and workflow managers include Nextflow, and Snakemake.Develops and maintains user documentation, onboarding materials, and training resources.Complies with all governmental policies, rules, regulations and codes.Coordinate with both IT and faculty oversight bodies to assure best practices for HPC environment management.Performs other duties as assigned.CERTIFICATIONS/SKILLS:Experience with Linux administration in an HPC or large-scale compute environment.Experience with Slurm workload management.Proficiency in Bash and at least one additional scientific scripting language (e.g. Python, R)Knowledge of scientific computing software and environment management.Familiarity with scientific workflow managers such as Nextflow or Snakemake.Strong written and verbal communication skills.Strong debugging, troubleshooting, and customer support skills.MINIMUM EDUCATION & EXPERIENCE:Bachelor’s Degree in Computer Science, Information Technology, Engineering, or related field.Three (3) years of experience in HPC systems administration, Linux administration, or related computational environments.