About this role
Platform Support Architect at DataDirect Networks. Location: San Francisco, California, United States. Role: supporting platforms, diagnosing issues, authoring runbooks Requirements: 5+ years Linux-based infrastructure experience (SRE/MLOps/L2-L3 support), deep Kubernetes/container and GPU experience, familiarity with NVIDIA AI Enterprise, vector DBs (Milvus), high-performance storage and RDMA networking, runbook and observability expertise. Category: Information Technology Seniority: Senior Level Tools: NVIDIA AI Enterprise, NIMs, NeMo, Triton Inference Server, Triton, TensorRT, TensorRT-LLM, GPU Operator, Milvus, Qdrant, Pinecone, pgVector, OpenSearch, Elasticsearch, Kubernetes, Docker, containerd, Helm, Operators, DaemonSets, CSI, CNI, ingress, Linux, DGX, HGX, Infinia, EXAScaler, Lustre, GPFS, Ceph, RDMA, InfiniBand, Prometheus, Grafana, ELK, NetQ, Loki, CUDA Commitment: Full Time Workplace: Remote Languages: cq, English