HPC System Administrator

As an HPC System Administrator at Qvelo, you will be responsible for managing and maintaining high-performance computing (HPC) systems that power advanced simulations, data analytics, and AI-driven workloads. Your expertise in system administration, cluster management, and performance tuning will ensure the reliability, security, and efficiency of our clients’ HPC environments. You will play a key role in troubleshooting issues, optimizing system performance, and ensuring that HPC resources are effectively utilized to meet the demands of large-scale, data-intensive applications.

Key Responsibilities:

• Install, configure, and maintain HPC clusters including compute nodes, storage systems, and high-speed networking components.
• Monitor system performance and troubleshoot issues related to hardware, software, and network connectivity, ensuring maximum uptime and availability.
• Manage job scheduling and workload management systems (e.g., SLURM, PBS, LSF) to optimize the use of HPC resources.
• Perform software upgrades, patches, and security updates across HPC environments, ensuring system stability and compliance with security protocols.
• Manage storage systems such as Lustre, GPFS, or NFS, ensuring efficient data access and management for large-scale workloads.
• Implement backup and disaster recovery strategies for critical HPC resources and data.
• Develop and maintain scripts and automation tools for routine system tasks, improving operational efficiency.
• Collaborate with HPC users to identify performance bottlenecks and recommend optimizations to improve system performance.
• Ensure network infrastructure is configured and optimized for low-latency, high-throughput communication between compute nodes.
• Document system configurations, processes, and troubleshooting procedures to ensure consistency and knowledge sharing within the team.

Requirements:

• Bachelor’s degree in Computer Science, Information Technology, or a related field.
• Proven experience in managing and administering HPC systems including installation, configuration, and maintenance of clusters.
• In-depth knowledge of Linux operating systems (e.g., CentOS, Ubuntu, RHEL) and shell scripting (Bash, Python).
• Experience with job scheduling systems such as SLURM, PBS, or LSF.
• Knowledge of parallel file systems (Lustre, GPFS) and storage management in HPC environments.
• Experience with networking technologies such as InfiniBand, Ethernet, and TCP/IP protocols for high-performance environments.
• Strong troubleshooting and performance tuning skills.
• Excellent communication and collaboration abilities, with a focus on supporting end-users in optimizing their HPC workflows.
• Familiarity with security best practices and implementation of system monitoring tools (e.g., Nagios, Ganglia).

Preferred Qualifications:

• Experience with cloud-based HPC or hybrid HPC environments (AWS, Azure, or Google Cloud).
• Familiarity with containerization technologies (e.g., Docker, Singularity) in an HPC context.
• Certifications in HPC systems administration or related technologies are a plus.
• Knowledge of GPU computing and how to manage GPU-accelerated HPC workloads