HPC Administrator

General Dynamics Information Technology; Hamilton (MT); Hybrid; USD 90,000 - 135,000; Full time

Job summary

General Dynamics Information Technology is seeking an HPC Administrator to join the Scientific Computing team at Rocky Mountain Laboratories in Hamilton, Montana. The hybrid role requires onsite presence 1-2 times per month to support HPC infrastructure and scientific software used by researchers.

You will install and maintain Linux-based compute nodes, support Slurm workloads, assist CryoEM workflows, and develop automation and documentation to improve reliability and usability of shared HPC

Qualifications

• Bachelor's degree in CS/engineering/scientific computing or related field; 5+ years of relevant experience.
• Experience in Linux-based HPC or research computing environments.
• Experience installing and supporting scientific software, compilers, and libraries.
• Familiarity with Slurm and shared scientific workloads.
• Experience with CryoEM packages such as RELION, cryoSPARC, Imod.
• Strong troubleshooting across software, environment, and user workflows.
• Scripting experience in Bash or Python.
• Familiarity with build/package tools like Spack/EasyBuild.
• Exposure to scientific apps and workflows in research environments.
• Experience with containers such as Apptainer/Singularity.

Responsibilities

• Administer, maintain, and troubleshoot Linux-based HPC infrastructure (compute nodes, login nodes, storage, services).
• Support deployment, configuration, monitoring, and lifecycle management of HPC hardware and core infrastructure.
• Assist with datacenter activities including hardware configuration, cabling, component replacement, and validation.
• Monitor system health, investigate performance issues, ensure reliability, availability, and security of shared HPC resources.
• Support researchers using Scientific workflows (CryoEM) by assisting with installation, maintenance, troubleshooting, and optimization of CryoEM software and HPC environments.
• Collaborate with researchers to ensure reliable execution of data processing pipelines and improve workflow performance on shared HPC resources.
• Develop and maintain operational documentation, automation scripts, and standard procedures to improve efficiency and reliability.

Skills

Linux HPC

Slurm

CryoEM software

Bash scripting

Python scripting

Troubleshooting

Onsite support

Container knowledge

Spack

EasyBuild

Education

Bachelor's degree in CS/Engineering/Scientific Computing

Tools

Relion

cryoSPARC

Imod

Apptainer/Singularity

Job description

We are seeking an HPC Administrator to join a Scientific Computing team supporting high-performance computing (HPC) and scientific research at NIAID. This role will provide local engineering support for HPC infrastructure and scientific software serving researchers, with strong emphasis on software installation, module support, systems troubleshooting, and scientific workflow enablement.

Biomedical research activities for a major federal health agency depend on the technologies and services you'll support in your role here at GDIT. Here, you'll be empowered to turn obstacles into action. Join us on the frontlines of scientific computing services and make an impact on the health of our nation.

This is a hybrid position located at Rocky Mountain Laboratories (RML), Hamilton, Montana. Onsite work will be required at least 1-2 times per month.

Responsibilities:

• Administer, maintain, and troubleshoot Linux-based HPC infrastructure, including compute nodes, login nodes, storage systems, and supporting services.
• Support the deployment, configuration, monitoring, and lifecycle management of HPC hardware, operating systems, and core infrastructure components.
• Assist with datacenter activities including hardware configuration, cabling, component replacement, and system validation during deployments and upgrades.
• Monitor system health, investigate performance issues, and help ensure the reliability, availability, and security of shared HPC resources.
• Support researchers utilizing Scientific workflows (such as CryoEM) by assisting with the installation, maintenance, troubleshooting, and optimization of CryoEM software applications and supporting HPC environments.
• Collaborate with researchers to help ensure reliable execution of data processing pipelines and to improve the performance and usability of their scientific workflows on shared HPC resources.
• Develop and maintain operational documentation, automation scripts, and standard procedures that improve the efficiency and reliability of HPC operations.

Required Skills:

• Bachelor's degree in computer science, engineering, scientific computing, bioinformatics, or a related field and at least 5 years of related experience.
• Experience working in Linux-based HPC or research computing environments
• Experience installing and supporting scientific software, compilers, and libraries
• Familiarity with job schedulers such as Slurm and supporting shared scientific workloads
• Experience supporting CryoEM software packages such as RELION, cryoSPARC, Imod or similar applications is highly desirable.
• Strong troubleshooting skills across software, environment, and user workflow issues
• Scripting experience in Bash, Python, or similar
• Familiarity with software build and package management tools such as Spack, EasyBuild etc
• Exposure to scientific applications and workflows used in research environments
• Experience with containers such as Apptainer/Singularity is a plus
• Ability to work closely with local stakeholders and provide dependable onsite support