感知模型剪枝量化 工程师
Core
Design and implement model pruning and quantization strategies to optimize perception models for efficient deployment on compute-constrained production platforms.
Role type
Senior IC machine-learning engineer (model compression)
Builds
Optimized perception models for autonomous driving/ADAS systems
Domain
Autonomous driving / Embedded AI
Deliverable
production ML models
Required skills
Deep learning (CNN/Transformer), Model pruning (structured/unstructured), Quantization (PTQ/QAT), INT8/FP16, PyTorch, TensorRT, ONNX Runtime, C++, Python, Performance analysis
Preferred skills
BEV perception models, NPU/BPU/GPU optimization, Automotive mass production delivery
Technologies
PyTorch, TensorRT, ONNX Runtime, DPX
Responsibilities
Design pruning/quantization schemes, build compression pipelines, analyze model sensitivity, establish regression validation processes
Seniority
Senior, hands-on IC
