Infra Support Engineer

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 r