Description
Lenovo is hiring a full-time AI Model Deployment Engineer in Shanghai to deploy autonomous-driving AI models on automotive heterogeneous computing platforms. The role covers model conversion, quantization, compilation, runtime adaptation, operator adaptation and custom operator development, inference optimization, deployment troubleshooting, and development of profiling and compatibility tools. The engineer will also coordinate with software, hardware, and integration-test teams for system integration and version delivery. Requirements include a bachelor's degree or higher in a relevant field, at least four years of AI model deployment or inference optimization experience, familiarity with PyTorch and ONNX, expertise in at least one automotive inference framework, and proficiency in Python and C/C++.
