Edge AI Extreme Optimization Engineer (TinyML Hacker)

[The Mandate ]|

[Core Tech Stack| Hard technical stack]

Bottom language: Proficient in C/C++, familiar with low-level memory management and concurrent programming.

Inference framework: Proficient in TensorRT, NCNN, ONNX Runtime, OpenVINO, etc., edge inference acceleration frameworks.

Model compression: with deep practical experience in model quantization (Quantization - INT8/INT4), network pruning (Pruning), and knowledge distillation (Distillation).

Hardware acceleration: familiar with CUDA programming, understand ARM NEON and other low-level instruction set optimization.

|

Have engineering landing experience in autonomous driving, robotics (SLAM / ROS) or vehicle-road collaboration (V2X).