Linux/HPC Systems Engineer

COLSA Corporation • Huntsville, AL

1d • Onsite

About The Position

In this role, your daily impact spans the entire spectrum of systems engineering. One hour, you might be performing routine lifecycle maintenance—patching a fleet of RHEL workstations or managing user identities across a heterogeneous domain—to ensure the baseline stability of our enterprise. The next, you are diving into the high-performance fabric, debugging a latency spike on an InfiniBand card or fine-tuning a Slurm scheduler to prioritize a mission-critical simulation. You aren't just managing boxes; you are the bridge between raw silicon and national security breakthroughs. Whether it's the methodical "hardening" of a standard server build to meet SAP requirements or the high-adrenaline optimization of a multi-petabyte Lustre filesystem, your work ensures that our researchers never have to wait on the infrastructure to catch up with their imagination. This position is 100% on-site.

Responsibilities

• Architect & Deploy: Lead the design and lifecycle management of mission-critical Linux workstations, enterprise-grade servers, and high-performance computing (HPC) clusters.
• Engineer Filesystems: Master the art of data movement. Administer complex local and distributed filesystems (Lustre, GPFS/Spectrum Scale) to ensure extreme-speed access across the fabric.
• Infrastructure as Code (IaC): Treat the data center as a codebase. Develop sophisticated automation workflows using Python, Bash, and Ansible to eliminate manual toil and ensure drift-free configurations.
• Defensive Engineering: Implement "Hardened by Design" security. Fine-tune SELinux policies and advanced firewall configurations to protect sensitive data without sacrificing computational performance.
• Container Orchestration: Modernize scientific workflows by deploying and managing isolated environments using Podman while working to establish a Kubernetes environment.
• HPC Performance Tuning: Push the limits of the silicon. Optimize cluster scheduling and management utilizing industry-leading tools like Bright Cluster Manager and Slurm.
• Low-Latency Networking: Configure and optimize high-bandwidth networking, including InfiniBand fabrics, for seamless inter-node communication.
• Technical Documentation: Author high-fidelity playbooks and strategic architectural diagrams that serve as the blueprint for our evolving infrastructure.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed