Systems Engineer, HPC/Storage

Columbia University Irving Medical Center (CUIMC), part of a premier Ivy League institution and home to nearly 100 Nobel laureates, advances world-class biomedical and computational research spanning cancer genetics, genomics, molecular biology, and AI-driven discovery. The CUIMC Central IT (CUIMCIT) High-Performance Computing (HPC) team supports this mission through a rapidly evolving research computing environment featuring advanced GPU platforms, large-scale parallel storage, hybrid cloud integration, and next-generation scientific software., * HPC Modernization & Infrastructure Engineering

• Support the ongoing modernization of CUIMC’s HPC environment, including GPU-accelerated computing, high-speed interconnects, and next-generation clusters.
• Contribute to lifecycle planning, hardware refreshes, and the integration of new compute and enterprise storage technologies.
• Expand hybrid cloud capabilities and campus-wide research computing.
• Server & Cluster Administration
• Manage and maintain high-performance research computing servers, including Enterprise Linux distributions (Red Hat / Rocky Linux), SLURM/HPC clusters, and database infrastructures.
• Monitor system performance, reliability, and capacity across compute nodes and shared infrastructure.
• Enterprise Storage & Big Data Management
• Administer large-scale parallel storage systems (such as VAST, Weka, or Isilon), including access control, quotas, advanced performance tuning, and backups.
• Support the modernization of high-speed storage platforms to meet exponential data demands in genomics, high-resolution imaging, and AI workloads.
• Scientific Software & Research Applications
• Maintain, optimize, and deploy high-performance environments for scientific applications and tool chains such as MATLAB, Python, R, CUDA, PyTorch, Jupyter, container runtimes (Apptainer/Singularity), Grafana, Open On Demand.
• Collaborate directly with researchers to troubleshoot computational workflows, optimize parallel jobs, and support emerging computational methodologies.
• Virtualization & Cloud Integration
• Manage KVM-based virtualization platforms and integrate on-premises infrastructure with campus and cloud resources.
• Support containerization, and modern DevOps practices where applicable.
• Identity & Access Management & Compliance
• Administer user accounts, multi-protocol permissions, and group policies within enterprise Active Directory environments.
• Enforce security best practices to ensure system stability, data integrity, and adherence to institutional compliance standards (e.g., HIPAA, NIST 800-53/171).
• Resource Accounting & Collaboration
• Manage computing resource allocations, usage tracking, and service metrics.
• Represent CUIMCIT in technical committees, change-management processes, and cross-functional research computing initiatives.
• Additional Duties
• Perform other responsibilities as assigned by the HPC Team Director.

We are seeking an experienced Systems Engineer, HPC & Storage to help modernize, operate, and support this mission-critical research infrastructure. The ideal candidate brings deep technical expertise, a strong service orientation, and the ability to collaborate effectively with faculty, postdoctoral researchers, graduate students, and technical teams. This position participates in a 24x7 operational model and may require occasional off-hours support for critical incidents., * Bachelor’s degree or equivalent in education and experience, plus four (4) years of related experience

• Expert-level proficiency in systems automation and scripting (e.g., Bash, Python, PowerShell).
• Strong command of TCP/IP and IB networking, and virtualization technologies.
• Excellent written/verbal communication skills and demonstrated customer-service orientation toward academic researchers.
• Ability to lift equipment up to 50 lbs., * Minimum of 2-4 years of hands-on experience supporting large-scale technical environments, preferably in HPC or research computing.
• Advanced degree in computer science, or related discipline.
• Professional certifications in Linux administration, enterprise storage, networking, or cloud technologies.
• Direct, hands-on experience managing enterprise parallel filesystems (e.g., VAST, Weka, Quobyte, Isilon) and workload managers (e.g., SLURM).
• Background in academic medical centers or high-performance research computing environments supporting sensitive data (PHI).
• Knowledge of modern ML/AI technologies.