Principal HPC System Administrator - JR28146-3800

University of Chicago - Chicago, IL

Full-time - Principal

Hybrid - Chicago, IL

Educational Services

About the position

The Principal HPC System Administrator at the University of Chicago's Research Computing Center (RCC) is responsible for designing, configuring, deploying, and maintaining high-performance computing (HPC) systems. This role requires specialized knowledge and expertise to develop automated and scalable solutions for infrastructure and server configuration. The position involves hands-on management of HPC resources, ensuring optimal performance and security, and providing technical leadership on complex projects.

Responsibilities

• Design, configure, deploy, and maintain large computer clusters, servers, and software.
• Perform day-to-day operations leadership, including systems administration, monitoring, and storage performance.
• Manage the system's network switch, parallel file system, and HPC software stack and tools.
• Monitor, maintain, and optimize HPC systems and software to improve performance and resource utilization.
• Serve as the technical lead on complex projects and system-related tasks.
• Configure, install, and maintain the job scheduler/workload manager.
• Diagnose and resolve system operational problems promptly and effectively.
• Use scripting/programming to enable system-level automation, monitoring, and problem detection.
• Build and deploy open-source software as well as software from vendors/partners.
• Develop and implement strategies for HPC data management, backup, disaster recovery, and security.
• Create standard operating procedures for routine and complex system tasks.
• Maintain and monitor the security of HPC systems and servers.
• Troubleshoot and identify failed hardware, implement parts replacement, and resolve system failures.
• Stay updated with the latest developments in HPC technologies and apply this knowledge to improve RCC systems.
• Provide expertise in planning and installing necessary patches and upgrades for servers.

Requirements

• Minimum college or university degree in a related field.
• 7+ years of work experience in a related job discipline.
• Experience with Linux system administration (e.g., RHEL, Rocky, CentOS).
• Proficiency in the installation, maintenance, operation, tuning, and troubleshooting of Linux and related systems and software.
• Experience in installing, configuring, and maintaining a job scheduler/workload manager (such as SLURM, TORQUE, or PBS).
• Experience configuring, installing, and troubleshooting MPI and OpenMP.
• Experience with at least one HPC cluster management tool (e.g., XCAT, Confluent, Warewulf, or Bright).
• Experience in configuring, administering, and supporting network storage subsystems.
• Hands-on experience with at least one parallel file system (e.g., Spectrum Scale-GPFS, Lustre, BeeGFS, or Ceph).
• Direct experience working with Infiniband and Gigabit Ethernet.
• Experience with networking and security.
• Experience with systems automation tools such as Ansible or Puppet.
• Experience with versioning tools such as Git or Subversion.
• Strong knowledge of scripting languages such as Python or bash.

Nice-to-haves

• Bachelor's degree in Computer Science or closely related field.
• Ability to work well with faculty and researchers.
• Ability to identify and gain expertise in appropriate new technologies and/or software tools.
• Ability to function as part of an interactive team while demonstrating self-initiative.
• Strong analytical skills and problem-solving ability.

Benefits

• Health insurance
• Paid holidays
• Professional development opportunities
• Flexible scheduling
• Tuition reimbursement