Data Center Ops

Data Center Ops is a real-time, on-device AI assistant that helps data center technicians inspect and assemble server racks correctly the first time. Over 1000 racks are built every week — dense meshes of cables, trays, and ports assembled at volume by labor crews cross-referencing paper guides. Roughly 80% are installed incorrectly on the first attempt. DC-Ops turns any Snapdragon phone into a smart inspection tool: point the camera at a rack and it instantly identifies 16 classes of components — compute trays, network ports, LEDs, cables, fans, drive bays, power shelves, DPUs and more — drawing live overlays on the camera feed. Everything runs entirely on-device using PyTorch and ExecuTorch, compiled to the Qualcomm QNN Hexagon Tensor Processor (HTP) NPU on the Samsung Galaxy S25 Ultra (Snapdragon 8 Elite, SM8750). This matters because data centers that manage private data have limited cloud availability but technicians need instant feedback. By running inference directly on the NPU with INT8 quantization, DC-Ops delivers low-latency, power-efficient detection with zero data ever leaving the device. We trained on 2,036 human-labeled images across four datasets, bootstrapped with a BrightData web-scraping + auto-labeling pipeline (Grounding DINO + SAM). Models and dataset are published openly on Hugging Face.