About the Role

You will own customer GPU clusters from installation through production use, working with our network and LLMOps teams to ensure each cluster is ready for training and inference. The role covers on-site data center work and long-term operations.

Responsibilities

Install and configure GPU servers on NVIDIA HGX platforms in line with NVIDIA Reference Architecture.
Perform validation and benchmarking before handover, including burn-in, NCCL tests and storage throughput.
Deploy and manage Slurm or Kubernetes for GPU workloads.
Implement monitoring for GPU utilization, temperature and hardware faults.
Diagnose and resolve driver, firmware and hardware issues with vendors.
Prepare handover documentation and runbooks for the operations team.

Qualifications

At least 3 years of experience administering Linux servers or HPC clusters.
Hands-on experience with NVIDIA drivers, CUDA and DCGM.
Proficiency in automation with Bash, Python or Ansible.
Solid understanding of data center networking and storage.
Willingness to travel to data centers in Thailand.

Preferred Qualifications

Experience with InfiniBand or RoCE on GPU clusters.
Experience with the NVIDIA GPU Operator on Kubernetes.
Certifications from NVIDIA, Red Hat or the Linux Foundation.

Tools and Technologies

Linux
NVIDIA HGX
CUDA
DCGM
Slurm
Kubernetes
Ansible
Prometheus

Working at Zotect

Work across the full AI infrastructure stack, from data centers, networking and GPUs to model serving.
Deliver production systems for customers in Thailand, Singapore and the United States.
Work closely with leadership in an engineering-led company.
Our office is located in the Gaysorn Building on Ploenchit Road, next to BTS Chit Lom.

How to Apply

To apply, send your CV and any relevant portfolio links to hr@zotect.com with the position title in the subject line.

Please include only the information needed to assess your application and omit sensitive data such as national ID numbers, religion or health information. For details, see our Privacy Policy