Description
The AI Application Engineer will enable, optimize, and deploy AI models on automotive-grade SoCs, including CNNIP, DSP, and NPU hardware. The role covers model performance analysis, post-training quantization, quantization-aware training, operator fusion, embedded runtime integration, debugging, ONNX-based toolchain support, and customer-facing evaluations and demonstrations. Candidates need a bachelor’s or master’s degree in a relevant field, deep learning and inference knowledge, hands-on experience with PyTorch, ONNX, or ONNX Runtime, strong Python skills, and familiarity with embedded systems.
