IT Administrator – HPC & Data Center Operations

About the role

Prepaire Labs is looking for an experienced IT Administrator to manage its high‑performance computing (HPC) and data‑center infrastructure that powers AI‑driven drug discovery and healthcare research. The role is based on‑site in Abu Dhabi and requires hands‑on responsibility for compute clusters, networking, software licensing and day‑to‑day IT operations.

Key responsibilities

• Administer, monitor and maintain CPU/GPU HPC clusters (NVIDIA H100/A100/L40S, AMD EPYC, Intel Xeon) and associated workload managers such as SLURM, PBS or Kubernetes with GPU orchestration.
• Deploy and update GPU drivers, CUDA toolkits, container runtimes (Docker, Singularity/Apptainer) and machine‑learning frameworks.
• Oversee data‑center operations including rack‑and‑stack, power and cooling monitoring (PDU/UPS), cable management, hardware lifecycle and capacity planning.
• Manage high‑performance storage solutions (NFS, Lustre, BeeGFS, Ceph, NAS/SAN) and backup/disaster‑recovery strategies.
• Design, configure and maintain LAN/WAN, VLANs, firewalls, VPNs, wireless and high‑speed interconnects (InfiniBand, RoCE, 10/25/40/100 GbE).
• Administer core network equipment (Cisco, Juniper, Arista, Fortinet, Mellanox/NVIDIA) and ensure secure remote access, redundancy and network segmentation for sensitive healthcare data.
• Handle procurement, deployment and compliance of scientific, healthcare and laboratory software licenses (LIMS, bioinformatics suites, molecular modelling tools, EHR/EMR integrations).

Required profile

• Proven experience administering HPC or data‑center environments with CPU and GPU workloads.
• Strong understanding of Linux system administration, networking and storage technologies.
• Ability to work on‑site, coordinate with vendors and support research teams in a regulated healthcare setting.

Required skills

• NVIDIA GPUs (H100, A100, L40S)
• AMD EPYC and Intel Xeon servers
• SLURM, PBS, Kubernetes
• CUDA, Docker, Singularity/Apptainer, NVIDIA Container Toolkit
• Grafana, Prometheus, Zabbix, Nagios, NVIDIA DCGM
• NFS, Lustre, BeeGFS, Ceph, NAS/SAN
• InfiniBand, RoCE, 10/25/40/100 GbE Ethernet
• Cisco, Juniper, Arista, Fortinet, Mellanox/NVIDIA networking gear
• IP address management (IPAM)
• LIMS, bioinformatics suites, molecular modelling tools, EHR/EMR integrations