Responsibilities
Assist in Modeling/Data Analysis projects as assigned.
Research and keep track of different deep learning training frameworks, explore and study methods for model optimization and compression.
Research and analyse the development trends of AI-related hardware products (such as chips, platforms), algorithms, and applications in the industry.
Deploy AI algorithm models on different platforms with productization integration and implementation.
Assist in regular product reviews and modifications
Travel to clients’ city for business meeting will be required
Requirements
Graduate in STEM-related discipline such as Computer Science, Electronic Engineering, Information Engineering or relevant discipline
Bachelor’s degree or above
Proficient in C/C++ programming and familiar with Python/Java.
Familiar with at least one deep learning framework, such as Caffe/TensorFlow/PyTorch
Familiar with deep learning model optimization techniques, such as distillation/pruning/quantization.
Familiar with computer architecture and embedded systems.
Experience in at least one toolkit for optimizing and deploying deep learning models, such as OpenVino/NCNN/TensorRT.
Experience in assembly language, SSE, and MMX instruction set programming is a plus.
Experience in GPU Programming (OpenCL, CUDA) is a plus.
Good command of written and spoken English or Chinese (Mandarin)
Self-motivated and good communication skills