HPC Network Engineer: Automation, AI-Driven Observability

Lawrence Berkeley National Laboratory; Berkeley (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Lawrence Berkeley National Laboratory's NERSC is seeking a Network Engineer, Platform, Automation & HPC/AI to advance the 1 Tb/s border network and an 800G/400G data center backbone supporting HPC workloads and a wide user base across scientific computing.

This role spans network engineering, automation, and software development, offering opportunities to architect solutions, improve latency, and contribute to modernizing data centers and edge services within a high-performance research

Responsibilities

• Implement, operate, maintain, and improve network automation and observability solutions.
• Contribute to Data Center modernization efforts and NERSC's Smart Facility initiative.
• Support design and delivery of network services for emerging needs (e.g., American Science Cloud).
• Continuously monitor and optimize network performance, focusing on latency, throughput, and fault tolerance.
• Create and maintain comprehensive network documentation, including topology diagrams.
• Collaborate with the Security Group to ensure data integrity and high availability.
• Share on-call rotation with colleagues and serve as escalation contact.
• Work on and resolve complex issues requiring in-depth analysis across variables.
• Exercise judgment in selecting methods and evaluation criteria for obtaining results.
• Build effective working relationships with technical partners across disciplines.
• Architect, develop, and establish technical direction for network automation and self-healing capabilities.
• Lead Data Center modernization efforts in support of Smart Facility and emerging needs.
• Build and integrate AI/ML-driven observability and predictive analytics.

Job description

Lawrence Berkeley National Laboratory's NERSC is seeking a Network Engineer, Platform, Automation & HPC/AI to advance the 1 Tb/s border network and an 800G/400G data center backbone supporting HPC workloads and a wide user base across scientific computing.

This role spans network engineering, automation, and software development, offering opportunities to architect solutions, improve latency, and contribute to modernizing data centers and edge services within a high-performance research