Senior HPC Storage Systems Engineer

Senior HPC Storage Systems Engineer

XCEL Engineering, Inc. is an award-winning small business that provides trusted information technology, engineering, consulting and project management solutions and services to federal agencies and organizations. Originally founded in 1971 by professional engineers at the University of Tennessee, XCEL was acquired in 2003 by U.S. Army and Navy veterans and in 2023 became a MartinFed company. XCEL Engineering is a part of IT Lab Partners (ITLP) which was created to support a leading research facility in the East Tennessee region in recruiting the best and the brightest technical talent. Considering joining our impressive team today!

Xcel Engineering is seeking a Senior HPC Storage Systems Engineer to design, operate and maintain clusters, servers, and workstations storage supporting services where science happens at ORNL! This position resides in the Emerging Technologies and Computing team in the Research Computing group in the Information Technology Services Directorate at Oak Ridge National Laboratory (ORNL). The Emerging Technology Computational Group facilitates goals through HPC systems engineering, integration, and support for the research community. By providing design, deployment, optimization, monitoring, and tooling support across multiple clustered storage infrastructures, we facilitate Lab-wide R&D projects. Our HPC clusters range in scope from just a handful of nodes to over fifty-thousand cores. We partner with ORNL research organizations to enable research excellence and delivery. We work with other clustered computing and HPC groups to help research programs identify the best solutions for their needs. When we build our customer's environments, our team collaborates to design, implement, and maintain the systems from inception to retirement.

Essential Functions

• Architect, deploy, and manage large-scale HPC storage systems, including parallel file systems such as Lustre, GPFS/Spectrum Scale, BeeGFS and WEKA
• Design, implement, and operate large-scale Ceph storage clusters for HPC and research workloads, delivering reliable, high-performance object, block, and file storage services
• Ensure the availability, performance, scalability, and security of production storage environments
• Administer and optimize enterprise storage platforms such as Qumulo and NetApp in support of HPC and research workloads
• Design, deploy, and maintain archival storage solutions including Spectra Logic BlackPearl and large-scale tape libraries to ensure long-term data preservation and accessibility
• Integrate high-performance, enterprise, and archival storage layers into cohesive tiered storage architectures that balance cost, scalability, and performance for diverse scientific workflows
• Leverage automation and monitoring solutions to minimize day-to-day maintenance while identifying opportunities to optimize system performance and management
• Collaborate with researchers and technical POCs to support large data workflows and optimize I/O performance for scientific workloads
• Automate storage provisioning, monitoring, and maintenance using scripting and configuration management tools
• Diagnose and resolve complex storage and I/O-related issues in high-throughput, low-latency HPC environments
• Evaluate emerging storage technologies (NVMe, object storage, hierarchical storage management, burst buffers) and contribute to strategic planning for future HPC systems
• Work with 24/7 operations staff to streamline monitoring and troubleshooting, significantly reducing the need for off-hours support
• Deliver ORNL's mission by aligning behaviors, priorities, and interactions with our core values of Impact, Integrity, Teamwork, Safety, and Service. Promote equal opportunity by fostering a respectful workplace.

Basic Qualifications

A BS degree in computer science, computer engineering, information technology, information systems, science, engineering, or related discipline and 8-12 years of relevant professional experience; or an equivalent combination of education and experience. Master's degree holders: 7-10 years of relevant experience. PhD holders: 4-6 years of relevant experience. Five (5) or more years managing UNIX/Linux systems. Demonstrated experience managing HPC storage and large-scale enterprise storage systems. Three (3) or more years working with configuration management and automation tools such as Git, Jenkins, Ansible, or Puppet. Proficiency with at least one scripting language (Bash, Python, Perl, etc.). Strong Linux administration and advanced troubleshooting experience. Experience supporting large data systems and/or HPC scientific workloads. Strong desire to innovate and evaluate new technologies for HPC and storage environments.