Platform Support Architect

📋 Description Act as NVIDIA AI Enterprise and vector DB expert for HyperPOD environments Own end-to-end triage across GPU, NVAIE, Milvus, Kubernetes, Docker, and Infinia Diagnose and resolve performance bottlenecks in RAG/agentic AI workflows Collect logs/telemetry across Linux, containers, Kubernetes, GPU stack, storage/network Author and maintain runbooks, diagnostics, and supportability assets 🎯 Requirements 5+ years Linux-based infra/SRE/MLOps or L2/L3 support Hands-on Kubernetes/Docker, Helm, Operators GPU workloads in production; NVIDIA GPUs, CUDA, GPU Operator Experience with AI storage and HPC networking (EXAScaler, Lustre, Ceph; RDMA/InfiniBand) Vector databases (Milvus, Qdrant, Pinecone, pgVector, etc.) Understanding of RAG/Generative AI workflows and GPU inference 🎁 Benefits