About this role
Platform Support Architect at DataDirect Networks (DDN). Location: San Francisco, California, United States. Role: triaging systems, authoring runbooks, designing architectures Requirements: 5+ years Linux-based infrastructure experience (SRE/MLOps/L2-L3) supporting production systems; strong Kubernetes/containers, GPU/NVIDIA stack, vector DBs (Milvus etc.), RAG/GenAI workflows, observability, and runbook authoring skills. Category: Engineering Seniority: Senior Level Tools: NVIDIA AI Enterprise (NVAIE), NIMs, NeMo, Triton, Triton Inference Server, TensorRT, TensorRT-LLM, GPU Operator, Milvus, Qdrant, Pinecone, pgVector, OpenSearch, Elasticsearch, Kubernetes, Docker, containerd, Helm, Operators, DaemonSets, CSI, CNI, Linux, CUDA, DGX, HGX, EXAScaler, Lustre, GPFS, Ceph, RDMA, InfiniBand, Prometheus, Grafana, Loki, ELK, NetQ Commitment: Full Time Workplace: Remote Languages: English