Scientist, Edge Inference & Optimization

Job description

"

• Develop model compression and optimization techniques for in-vehicle edge devices
• Build low-power, high-performance edge inference algorithms
• Drive efficient model deployment on automotive chips
• Architect an end-cloud collaborative intelligent computing framework" "
• 3+ years in embedded AI or model optimization; proficient in TFLite, ONNX, TensorRT
• Proven experience deploying large models on heterogeneous compute platforms (NPU/GPU)
• Expert in model compression (quantization, pruning, distillation); able to independently lead edge inference optimization
• Strong low-level system optimization and chip co-design capabilities"