Senior UNIX HPC Systems Administrator

Department:

The Division of Information Technology (DoIT) has approximately 85 full time staff members and 100 undergraduate or graduate students that work each day to support the mission of UMBC through the delivery of IT services to the campus. DoIT provides robust, secure IT environments that enable solutions for advancing the UMBC community. We do this through a staff of technology professionals that are connected both nationally and to UMBC.

Learn more about our work at https://doit.umbc.edu/eis/unix-and-windows/

Position Overview:

The Senior UNIX HPC Administrator is part of a team that is responsible for the day-to-day operations of the research computing infrastructure managed by the Division of Information Technology.

The position will utilize modern system administration techniques such as orchestration, automation, and containerization to build software, deploy updates, provision new systems, manage configuration states and troubleshoot existing deployments.

Why Work at UMBC?

UMBC offers competitive compensation.  This role starts at $121,000 and has over 4 weeks of vacation for regular full time roles. Tuition remission is also available.

What is it like to work at UMBC?  Check out Glassdoor or Indeed. And read about our recent award, UMBC is a 2023 Great College to Work for…. In every category.

Telework:

A hybrid telework schedule is available!

Responsibilities:

Specific responsibilities include: 

• Work closely with various IT groups and departments, including but not limited to, Networks, Windows Administration, Security, Application, and Middleware Administration to assist in overall architectural design, implementation and troubleshooting
• Develop and maintain operational guidelines for the maintenance and support of the HPC/Research environments
• Design, troubleshooting, and maintenance of the following Software: NVIDIA Bright Cluster Manager, Red Hat Enterprise, Slurm
• Linux system administration, security patching, OS upgrades, troubleshooting problems, and ensuring maximum availability
• Work both independently and collaboratively with teams to troubleshoot service issues
• Assist researchers with software builds, environment configuration, and technical support
• Provide excellent customer service skills and demonstrate the ability to work with all levels within the organization, assuring prompt, and effective responses to customer needs
• Utilize standard communication, reporting and documentation tools to effectively and efficiently communicate with the team, and document technical solutions
• Help develop project plans, effectively create/update issues and keep team leads and management informed of changes, impediments, and updates
• Perform additional duties as assigned

Required Minimum Qualifications:

• Bachelor's Degree with at least 5-7 years experience working in a UNIX system administrator or engineering role with direct experience with at least some HPC technologies. Some of these technologies include: 
  • Cluster management
  • Parallel computing
  • Slurm or other workload managers
  • GPU programming and support
  • Building software for multiple computing architectures
• Experience with NVIDIA Bright Cluster Manager or other cluster management software
• Experience with versioning tools such as Git or Subversion
• Install and/or configuration of CEPH, parallel or high performance file systems
• Slurm or other cluster computing job management
• Server class hardware deployment and remote management
• Experience in the installation, maintenance, operation, tuning and troubleshooting of Linux and related systems and software
• Ability to install, modify, integrate, and configure commercial and open source software applications and utilities
• Experience supporting customer requests and working with stakeholders to gather and fulfill project requirements
• Capable of managing time effectively, working both independently and