NVIDIA GPU Server Hardware Infrastructure Engineer
Posted Updated
Description
JOB DESCRIPTION
The NVIDIA GPU server hardware requirement is for candidates with NVIDIA GPU configuration or architecture exposure, supported by infrastructure skills such as cloud infrastructure, storage management, and Kubernetes configuration on bare-metal or virtual-machine environments. Candidates need to understand CPU and RAM configuration, storage allocation, and ideally GPU allocation for AI model hosting.
The primary requirements are infrastructure expertise in GPU and CPU configuration and Kubernetes setup, including configuring GPU resources, establishing the Kubernetes environment, and hosting LLM or SLM models. The role requires experience in designing and implementing GPU infrastructure rather than responding to hardware requests.
REQUIREMENTS
The NVIDIA GPU server hardware requirement is for candidates with NVIDIA GPU configuration or architecture exposure, supported by infrastructure skills such as cloud infrastructure, storage management, and Kubernetes configuration on bare-metal or virtual-machine environments. Candidates need to understand CPU and RAM configuration, storage allocation, and ideally GPU allocation for AI model hosting.
The primary requirements are infrastructure expertise in GPU and CPU configuration and Kubernetes setup, including configuring GPU resources, establishing the Kubernetes environment, and hosting LLM or SLM models. The role requires experience in designing and implementing GPU infrastructure rather than responding to hardware requests.
REQUIREMENTS
- NVIDIA GPU configuration and architecture exposure
- Cloud infrastructure experience with AWS, Bedrock, or Azure OpenAI Foundry
- Storage management expertise
- Kubernetes configuration on bare-metal or virtual-machine environments
- Understanding of CPU and RAM configuration and storage allocation
- GPU allocation for AI model hosting
- Experience designing and implementing GPU infrastructure architecture
- Kubernetes setup and GPU resource configuration
- Experience hosting LLM or SLM models
- Direct experience with NVIDIA GPU models, hosting environments, and GPU allocation (preferred)
- Experience with CUDA, Run:AI, and Terraform automation (additional, not essential)