HPC Engineer

Overview

The National Center for Computational Sciences (NCCS) at the Oak Ridge National Laboratory (ORNL) is responsible for providing computational resources at extreme scales for science. NCCS is home to some of the fastest supercomputers and storage systems in the world including Frontier, the first supercomputer to break the exascale barrier and Orion, a 700 petabyte Lustre parallel file system. NCCS serves multiple agencies including DOE, NOAA, and the Air Force.

The NCCS also supports the center's Quantum Computing User Program (QCUP) which provides access to state-of-the-art quantum computing resources.

The NCCS User Assistance (UA) Group provides technical support to the center's advanced computing resources including high-performance computing (HPC), artificial intelligence, and quantum, generates documentation about NCCS systems, and develops and delivers training to users of the center's resources. NCCS staff members are also responsible for developing tools and technical solutions for users of these resources. NCCS HPC engineers also serve as ambassadors for users of these resources and the rest of the organization.

• Take technical ownership of user reported problems and provide hands‑on support for scientific applications and libraries and users of high‑performance computing, clusters, artificial intelligence, quantum, and other advanced computing resources.
• Compile and debug large science and engineering applications.
• Identify and resolve system‑level bugs in conjunction with other technical staff.
• Work with vendors to resolve issues and implement changes as necessary.
• Install third‑party software applications and tools and provide documentation for usage.
• Develop and execute system tests to ensure newly deployed systems can support user workloads.
• Proactively ensure that users have up‑to‑date information about the system, including any changes and their impact on the users. User Assistance staff are very involved in researching and developing documentation and reference material during system early‑use and upgrade phases, as well as maintaining them throughout system operation.
• Participate in the development, maintenance, and delivery of training and outreach materials to users.
• Respond to general administrative questions (e.g., system status, requests for special accommodation, etc)
• Implement special projects as requested (e.g., metrics, cyber security, policy discussions).
• Actively participate and advocate for users during planning of system configuration, policy creation, outages, and other user impacting events.

• Bachelor's Degree in computer science or related field or equivalent experience with 5 years of experience, MS Degree with 4 years of experience, or a PhD
• Experience providing user support
• Requires practical experience with multiple programming languages and technologies including several of the following:
• Fortran
• C
• C++
• Perl
• Python
• Shell scripting (e.g., bash, ksh, etc.) in a Linux or Unix environment

• Experience building and installing scientific software and other 3rd party software applications on HPC systems
• Experience with HPC schedulers and resource managers
• Experience executing scientific software on HPC systems
• Experience writing user documentation
• Experience developing and delivering training for users
• Strong technical and analytical skills
• Strong verbal and written communication skills
• Maintains the highest level of professionalism at all times when interacting with internal and external customers
• Demonstrates a high‑energy, positive attitude and commitment to quality customer service
• Contributes to a positive team environment within the center by demonstrating a strong work ethic, effectively communicating with others, and proactively anticipating center and user needs
• Experience coordinating and running support teams
• Understanding of the requirements of a DOE, DoD, and/or NSF HPC center

For employment at Oak Ridge National Laboratory (ORNL), a Real  form of identification will be required. Additionally, ORNL is subject to Department of Energy (DOE)…