SRE for HPC Infra & Automation — Overnight (Contract)

ltdglobal; Berkeley (CA); Hybrid; USD 96,000 - 124,000; Part time

Job summary

ltdglobal is seeking a sharp, self-motivated Site Reliability Engineer to support a national HPC facility in Berkeley, CA. This 1-year contract assignment offers $80/hr with a possibility of extension based on performance and organizational needs.

You will monitor and triage real-time alerts across compute, storage, network and facility systems; build automation to prevent outages; develop monitoring tools and integrations; and walk the data center floor to maintain power, cooling, and

Qualifications

• Solid Linux/command-line (SSH) chops.
• Programming/scripting experience: Python, C, C++, Perl, or Java.
• Self-starter mindset, eager to pick up Kubernetes, Prometheus/VictoriaMetrics, Alertmanager, and building management/cooling systems.
• Comfortable with Owl shift (12am–8am), five days/week, hybrid onsite in Berkeley, CA.
• Strong cross-team communication and collaboration skills.

Responsibilities

• Monitor and triage alerts across compute, storage, network, and facility systems in real time.
• Build automation that prevents issues before outages occur.
• Develop new tools and integrations across the monitoring pipeline (APIs → alerts → action).
• Walk the data center floor to keep power, cooling, and environmental systems humming.
• Coordinate maintenance activities across teams and keep incidents accurately tracked.
• Dig into complex, ambiguous problems and drive them to resolution.

Skills

Linux CLI

Python

C/C++

Perl

Java

Kubernetes

Prometheus

VictoriaMetrics

Alertmanager

Networking security

Cross-team collaboration

Tools

ServiceNow

ITSM

Job description

ltdglobal is seeking a sharp, self-motivated Site Reliability Engineer to support a national HPC facility in Berkeley, CA. This 1-year contract assignment offers $80/hr with a possibility of extension based on performance and organizational needs.

You will monitor and triage real-time alerts across compute, storage, network and facility systems; build automation to prevent outages; develop monitoring tools and integrations; and walk the data center floor to maintain power, cooling, and