SYSTEMS ENGINEER PRINCIPAL (HPC/AI System Administrator, Multi-discipline Expert)

General Dynamics Information Technology

3d•Remote

About The Position

Advance how our customers operate while you advance your career. Join GDIT as a Systems Engineer Principal and build an impactful career in enterprise IT, collaborating with people who are driven and resourceful like you. MEANINGFUL WORK AND PERSONAL IMPACT As a Systems Engineer Principal, the work you’ll do at GDIT will be impactful to the mission of NOAA’s National Weather Service (NWS). You will play a crucial role in sustaining and improving the High Performance Computing (HPC) systems that generate the nation’s operational weather and climate forecasts, enabling NWS to deliver timely, accurate information that protects life and property.

Requirements

Bachelor of Arts/Bachelor of Science
8+ years of related experience
Linux system administration (Rocky/SLES preferred)
Experience with HPC batch schedulers (PBS Pro, Slurm, or similar)
Scripting abilities (Bash, Python, Perl)
Understanding of HPC architectures, distributed computing, and MPI-based workloads
Troubleshooting skills across multi-node HPC environments
US citizenship required
Ability to participate in an on-call rotation supporting 24/7 operational systems
Occasional travel for team collaboration, training, or customer interaction
Ability to work independently as well as collaboratively within a distributed technical team

Nice To Haves

Complex Systems
High Performance Computing (HPC)
Red Hat Enterprise Linux (RHEL)
System Performance
Systems Management

Responsibilities

Lead/Manage/Support daily HPC system operations and the reliability of the scheduling and system software stack that powers NOAA’s 24/7 numerical weather prediction mission
Collaborate with experienced GDIT HPC engineers, system administrators, developers, and NWS operational staff to troubleshoot issues, enhance system performance, and ensure consistent delivery of high‑impact forecasting products
Drive improvements in system efficiency, scheduler reliability, job throughput, and operational resiliency by analyzing complex problems, proposing innovations, and supporting implementation of technical enhancements
Utilize Linux system administration, HPC scheduler expertise (PBS Pro/Slurm), scripting languages, performance monitoring tools, and parallel computing technologies to keep two large‑scale supercomputing systems running at peak performance