Senior HPC Cluster Engineer

About the Role

NVIDIA is seeking a Senior HPC Cluster Engineer for its MARS team in Bengaluru. You will lead strategic guidance and operations on large-scale High-Performance Computing (HPC) systems, managing compute, networking, and storage infrastructure essential for AI research.

Key Responsibilities:

• Provide leadership in system administration, service delivery, incident response, and reliability improvements for our global GPU fleet.
• Collaborate with global teams to deliver world-class user experiences for AI/HPC researchers.
• Own day-to-day operations of production clusters, ensuring health, efficiency, and resource optimization.
• Develop scalable automation solutions and maintain heterogeneous clusters on-premises and in the cloud using tools like Terraform, Ansible, and Docker/Singularity.
• Optimize cluster performance by analyzing job fragmentation, GPU waste, and tuning workloads for SLA targets.
• Conduct root cause analysis, lead SEV triage postmortems, and participate in on-call rotations for critical production environments.