Summary

Design and develop the end-to-end compilation pipeline for Qualcomm AI Hub, handling PyTorch and ONNX model ingestion, graph optimization, and deployment across CPU, GPU, and NPU backends on Snapdragon SoCs. Own compilation infrastructure, ONNX-based and PyTorch compilation paths, ONNXRuntime QNN execution provider contributions, and tooling for profiling and debugging. Scale model onboarding through automated CI/CD pipelines and partner with internal teams to translate deployment constraints into compilation strategies. Build developer-facing diagnostics, documentation, and tutorials for the AI Hub community.