Operating System Analyst/Administrator

An Emory College Research Support (ECRS) Senior Operating System Analyst/Administrator supports and administers Linux-based high-performance computing (HPC) systems with a primary focus on educational and instructional computing. Working with faculty, instructors, students, and other technical staff, this position helps provide reliable, accessible, and effective computing environments for courses that use Linux, HPC, GPU, and other computational resources.

The position is responsible for the administration, maintenance, monitoring, and troubleshooting of Linux servers, HPC clusters, and related infrastructure. A significant part of the role involves administering technologies that provide students and instructors access to computational resources, including Open OnDemand and Slurm-based computing environments.

This is a role intended for an administrator who can independently manage Linux systems and troubleshoot moderately complex infrastructure problems. The administrator is expected to possess a working knowledge of HPC concepts while continuing to develop expertise in cluster computing, storage, networking, automation, GPU computing, and other advanced technologies.

The position may also support research computing infrastructure and collaborate with researchers whose computational requirements overlap with the technologies and services provided for educational computing., * Plans and implements one or more muli-platform operating systems, utilities, and related software to meet organizational needs.

• May be responsible for applications on dedicated servers.
• Ensures the availability, integrity and reliability of assigned systems., * Administer and maintain HPC clusters and other Linux-based computing environments used by students and faculty.
• Administer, configure, maintain, and troubleshoot Open OnDemand environments providing web-based access to computational resources.
• Administer and troubleshoot Slurm workload-management environments, including nodes, partitions, resource allocation, job scheduling, and common user issues.
• Collaborate with faculty and instructors to prepare computing environments for courses, including determining resource requirements, configuring software, provisioning access, and testing environments before instructional use.
• Provide advanced technical assistance to faculty, instructors, teaching assistants, and students using Linux and HPC resources.
• Manage Linux user accounts, groups, permissions, SSH access, authentication, and integration with centralized identity-management systems.
• Install, configure, patch, upgrade, and troubleshoot Linux operating systems and applications.
• Install, configure, and maintain software required for instructional and computational workloads.
• Support GPU-enabled computing environments and assist users with accessing GPU resources through the workload scheduler.
• Perform operating system patching, security updates, vulnerability remediation, and other routine security administration.
• Monitor system availability, utilization, capacity, and performance and proactively identify potential problems.
• Diagnose and resolve hardware, operating system, storage, networking, authentication, scheduling, and application problems.
• Develop and maintain system administration documentation, operational procedures, configuration standards, and user-facing documentation.
• Use scripting and automation to improve system administration, deployment, configuration, and maintenance processes.
• Participate in infrastructure upgrades, migrations, hardware deployments, and other computing projects.
• Assist with evaluating new technologies and recommend improvements to instructional computing environments.
• Provide technical guidance and assistance to junior administrators and student employees when appropriate.
• Participate in the support of research computing systems when needed and apply experience gained across educational and research environments.

• Five years of operating systems analysis/administration experience OR a bachelor’s degree and three years of operating systems analysis/administration experience., * Professional experience administering Linux servers or comparable Linux infrastructure.
• Demonstrated proficiency with the Linux command line and core Linux administration concepts, including filesystems, permissions, processes, services, package management, system logging, and system configuration.
• Experience installing, configuring, maintaining, and troubleshooting Linux operating systems.
• Working knowledge of TCP/IP networking, DNS, SSH, and network troubleshooting.
• Experience administering multiuser Linux systems.
• Experience with shell scripting and/or a general-purpose scripting language such as Bash or Python.
• Experience diagnosing and resolving system administration problems independently.
• Understanding of fundamental security practices for Linux systems, including patching, access control, privilege management, and vulnerability remediation.
• Ability to document technical configurations, procedures, and troubleshooting information clearly.
• Ability to communicate effectively with users possessing a wide range of technical experience.
• Ability to manage multiple technical responsibilities and determine when issues require escalation or collaboration.
• Demonstrated ability to learn and independently apply unfamiliar technologies.
• A bachelor’s degree in computer science, information technology, engineering, a scientific discipline, or a related field is desirable, although equivalent of education and experience will also be considered.

Experience with several of the following is desirable:

• Open OnDemand administration and configuration
• Slurm workload management
• Administration of Linux-based HPC or cluster computing environments
• Supporting computing resources used for classroom instruction
• Configuration-management and automation tools such as Ansible
• Git or other version-control systems
• LDAP or other centralized authentication and identity-management systems
• GPU computing and scheduling GPU resources
• NFS or other network filesystems
• System and infrastructure monitoring
• Virtualization or container technologies
• Scientific or computational software environments

Candidates are not expected to be experts in every component of a HPC environment. However, a candidate should have sufficient Linux and infrastructure experience to independently investigate unfamiliar systems, understand their role within the larger environment, and develop proficiency as needed.

Depending on assignments and existing experience, the administrator may work with or develop deeper expertise in technologies such as:

• BeeGFS and other parallel filesystems
• ZFS and advanced storage technologies
• InfiniBand and other high-speed networking
• Advanced GPU resource management
• HPC cluster architecture and performance
• Splunk administration
• Configuration management and infrastructure automation
• Containers and application environments
• Scientific and research software stacks
• Hardware installation, diagnosis, and lifecycle management
• System, application, and infrastructure monitoring
• Research computing environments

Emory University is a leading research university that fosters excellence and attracts world-class talent to innovate today and prepare leaders for the future. We welcome candidates who can contribute to the excellence of our academic community.