Infra Support Engineer

Title: Infra Support Engineer - Fuku

URL Source: https://apply.workable.com/j/03C688AFC9

Markdown Content: Infra Support Engineer – GMI Global Infrastructure Team

Preferred Location:

• Taiwan

• Malaysia

Responsibilities:

• Provide first and second-line technical support to customers for AI Infrastructure, including GPU/CPU nodes, networking, storage, orchestration, and platform services. Support is delivered via ticketing systems, emails, Slack, or other messaging platforms.

• Support GPU cluster delivery, including system provisioning, image deployment, network validation, BIOS/firmware updates, and GPU driver/runtime installation.

• Monitor system health and service-level indicators using alerts and dashboards; respond to alerts 24x7 as scheduled.

• Triage incidents by gathering context, verifying scope and impact, and following standard operating procedures and runbooks to perform immediate mitigations.

• Escalate incidents to global SRE engineers with clear, concise incident notes and relevant logs/traces.

• Maintain incident logs, update status pages, and communicate timely updates to stakeholders during incidents.

• Perform routine operational tasks such as log checks, health checks, capacity checks, and simple automated fixes.

• Participate in postmortems and contribute actionable follow-ups to reduce recurrence of incidents.

• Help maintain and improve standard operating procedures (SOP), run periodic runbook validation, and document new procedures.

• Work collaboratively with developers and SRE teams to improve system reliability.

Qualifications:

• Bachelor’s degree in Computer Science or a related field.

• Over 2 years of experience in IT operations, server administration, SRE, DevOps, or technical support.

• Hands-on Linux experience, including shell, kernel, and log management.

• Basic networking knowledge, including TCP/IP, DNS, HTTP, and VLANs.

• Familiarity with monitoring, alerting, and logging tools such as Prometheus, Grafana, and AlertManager.

• Experience with Nvidia GPU infrastructure and Kubernetes.

• Comfortable collecting diagnostics, reading logs, and interpreting traces.

• Strong troubleshooting mindset and ability to follow runbooks under pressure.

• Excellent written and verbal communication skills for customer-facing incident handling.

• Willingness to work shifts and participate in on-call rotations.

• Bilingual in English and Chinese.