1. Responsible for the developing of deep learning models and related intelligent systems for the supply chain and logistics of international E-Commerce business.
2. Participate in the process of optimizing the business results by using some of the following techniques: computer vision, natural language processing, sales prediction, time-series, geo-coding, etc..
3. Keep track of cutting-edge technologies in the fields of computer vision, natural language processing and multi-modal machine learning; make use of these technologies to optimize the results in tasks such as fine-grained product style analysis, product similarity analysis and product attribute recognition, etc.
1. Have in-depth study in a certain field of natural language processing or computer vision, including but not limited to: image/video classification and recognition, image segmentation, object detection, OCR, graph neural network, text classification, NER, multimodal, unsupervised and self-supervised learning;
2. Familiar with at least one framework of TensorFlow / PyTorch / MXNet and its training and deployment details, as well as the training acceleration methods such as mixed precision training and distributed training;
3. Familiar with the latest research and technology in model compression acceleration, including but not limited to model quantization, pruning, knowledge distillation, as well as inference frameworks such as TensorRT;
4. Have strong practical ability, winners in Kaggle, COCO, ImageNet, NOI/IOI and other competitions are preferred, and those who have papers published in relevant competitions and top academic conferences (such as CVPR, ICCV, ECCV, ACL, EMNLP, etc.) are preferred as well;
5. Familiar with AutoML related algorithms, preferably with experience in automatic search of network structure or hyper parameters;
