HighPerformance Computing ( HPC) Administrator

Job Summary

We are seeking an experienced HPC Administrator to manage, optimize, and support our highperformance computing infrastructure. This role involves maintaining largescale clusters, ensuring system reliability, and enabling researchers, engineers, and data scientists to run computeintensive workloads efficiently.

Key Responsibilities

• Install, configure, and maintain HPC clusters, nodes, and associated hardware.
• Manage job scheduling systems (e.g., Slurm, PBS, Torque, Grid Engine).
• Monitor cluster performance, troubleshoot issues, and optimize resource utilization.
• Implement and maintain storage solutions (parallel file systems like Lustre, GPFS, BeeGFS).
• Ensure system security, patching, and compliance with organizational policies.
• Support users in running scientific, engineering, and AI/ML workloads.
• Automate administrative tasks using scripting (Bash, Python, Ansible).
• Collaborate with researchers to optimize applications for HPC environments
• Maintain documentation for system architecture, processes, and best practices.
• Plan and execute upgrades, expansions, and performance tuning.
• Provide training and technical support to endusers.

Required Skills & Qualifications

• 1-3 years of experience in Linux system administration, preferably in HPC environments.
• Strong knowledge of Linux operating systems (RHEL, CentOS, Ubuntu).
• Experience with HPC workload managers (Slurm, PBS, Torque).
• Familiarity with MPI, OpenMP, CUDA, or GPU computing.
• Knowledge of networking (InfiniBand, highspeed interconnects).
• Handson experience with monitoring tools (Nagios, Ganglia, Prometheus).
• Proficiency in scripting and automation (Bash, Python, Ansible).
• Experience with containerization (Singularity, Docker) in HPC contexts.
• Implement resource scheduling and workload management tools (Slurm, Kubernetes GPU scheduling).
• Strong troubleshooting and performance optimization skills.

Education & Certifications

• Bachelors or Masters degree in Computer Science, Engineering, or related field.
• Certifications such as RHCE, CompTIA Linux+, LPIC, or HPCspecific training preferred.

Desired Attributes

• Ability to work closely with researchers and technical teams.
• Strong analytical and problemsolving skills.
• Commitment to system reliability and performance.
• Adaptability to emerging HPC technologies (cloud HPC, AI/ML workloads).