Infrastructure Support Lead (AI)

Location: Based in Korea, with up to 25% international travel. Support coverage includes Asia hours, on-call, and out-of-hours escalation coverage across time zones.

Company

hirify.global builds high-performance AI systems with full-stack software supporting PyTorch and vLLM for production inference workloads.

What you will do

• Manage the support team and maintain consistent service delivery standards.
• Act as the senior technical point of contact for customer issues, driving resolution or routing issues to the appropriate engineer.
• Design and operate the support model, including intake, triage, escalation paths, and workflows connecting customers, partners, and internal teams.
• Own internal and customer-facing knowledge bases, runbooks, troubleshooting guides, and documentation.
• Implement and operate ticketing and field service management tools.
• Drive hardware service workflows covering RMA, spares, dispatch, and coordination with global support partners.

Requirements

• 8+ years of experience in technical support, field service, or service delivery for hardware deployed at customer sites.
• 2+ years working with AI/ML infrastructure or accelerated compute environments and 2+ years leading support or field engineering teams.
• Ability to lead technical debugging calls, read logs, reason across the hardware/software boundary, and distinguish configuration, firmware, and silicon issues.
• Hands-on experience with Linux, Kubernetes, containerized inference serving, and Python automation.
• Experience supporting external customers with hardware faults, software issues, performance problems, and major enterprise or government incidents.
• Professional Korean and English fluency required; based in Korea.

Nice to have

• Background in AI/ML, HPC, data center infrastructure, accelerators, or GPU systems.
• Experience with distributed LLM inference orchestration, including vLLM disaggregated serving, NVIDIA Dynamo, llm-d, or equivalent systems.
• Experience with PyTorch, inference optimization, performance tuning, data center integration, and multi-layer performance diagnosis.
• Experience implementing field service systems, KCS knowledge management, AI-assisted support operations, or supporting air-gapped sites.
• Experience with controlled hardware movement, structurally different markets, or product supportability requirements before release.

Culture & Benefits

• Work across global delivery and support partners and technical and business teams.
• Support production systems deployed across multiple regions, enterprises, and governments.
• International travel of up to 25% is part of the role.

Hiring process

• Application screening followed by an online interview.
• On-site interview including an assignment, followed by management and culture-fit interviews.
• Compensation discussion and final offer.