Role Summary:
Manage and support Kubernetes-based infrastructure on AWS, automate deployments using Terraform and CloudFormation, and validate NVIDIA GPU AI clusters for performance, stability, and production readiness.
Key Responsibilities:
• Administer and support Kubernetes/EKS clusters.
• Automate infrastructure provisioning using Terraform and AWS CloudFormation.
• Execute GPU cluster validation and benchmarking (NCCL, DCGM, NVBandwidth, OSU, iPerf, NHC).
• Monitor, troubleshoot, and resolve cluster performance issues.
• Validate InfiniBand/RDMA networking performance.
• Prepare validation reports and provide production readiness recommendations.

Must-Have Skills:
• Kubernetes (EKS)
• Terraform
• AWS CloudFormation
• Linux Administration
• AWS Cloud Services

Preferred Skills:
• NVIDIA GPU Platforms
• NCCL, DCGM, NVSM
• InfiniBand / RDMA Networking
• Performance Benchmarking & Troubleshooting

Experience:
• Hands-on experience with Kubernetes, Terraform, AWS, and Linux administration.
• Exposure to GPU/HPC/AI cluster environments is highly desirable.





Provide your feedback on BizChatRole Summary:
Manage and support Kubernetes-based infrastructure on AWS, automate deployments using Terraform and CloudFormation, and validate NVIDIA GPU AI clusters for performance, stability, and production readiness.
Key Responsibilities:
• Administer and support Kubernetes/EKS clusters.
• Automate infrastructure provisioning using Terraform and AWS CloudFormation.
• Execute GPU cluster validation and benchmarking (NCCL, DCGM, NVBandwidth, OSU, iPerf, NHC).
• Monitor, troubleshoot, and resolve cluster performance issues.
• Validate InfiniBand/RDMA networking performance.
• Prepare validation reports and provide production readiness recommendations.

Must-Have Skills:
• Kubernetes (EKS)
• Terraform
• AWS CloudFormation
• Linux Administration
• AWS Cloud Services

Preferred Skills:
• NVIDIA GPU Platforms
• NCCL, DCGM, NVSM
• InfiniBand / RDMA Networking
• Performance Benchmarking

📌 Senior Administrator (Hyderabad)
🏢 HCLSoftware
📍 Hyderabad