Staff AI Application Engineer
Core
Deploy and optimize BEV, object detection, segmentation, and classification models on Gen4/5 automotive SoC platforms using CNNIP, DSP, NPU, and HWA acceleration.
Role type
Staff AI Application Engineer (Automotive Embedded Systems)
Builds
AI inference pipelines for automotive perception systems on embedded SoC platforms
Domain
Automotive AI / Embedded Systems / Computer Vision
Deliverable
production ML models
Required skills
Deep learning fundamentals, PyTorch, ONNX, ONNX Runtime, Python, C/C++, embedded systems debugging, latency/throughput analysis, operator fusion, quantization-accuracy mitigation, Linux/QNX runtime integration, SIL/HIL validation
Preferred skills
Model training/fine-tuning, automotive/robotics use cases, embedded NPU/DSP/GPU/CPU inference optimization, INT8 calibration, automotive SoCs, QNX, memory hierarchy/DMA/multi-core scheduling, ONNX graph debugging
Technologies
PyTorch, ONNX, ONNX Runtime, Linux, QNX, CNNIP, DSP, NPU, HWA, Python, C/C++
