Algorithm Engineer (Computer Vision), e-Commerce department of An Internet Giant

About the team

The team uses the most advanced AI technology to combat various risks/violations in the Company's e-commerce platform, maintain platform security, build a good e-commerce ecosystem, and empower business teams to improve work efficiency. We pursue the ultimate risk detection capability. The fairness and sustainability of the e-commerce ecosystem, high-quality content, and merchandise are areas where we are constantly striving for improvement.

Responsibilities

1. Responsible for the optimization and iteration of computer vision related models in the e-commerce scene, including fine grain classification, product object recognition, product subject recognition, feature extraction, logo detection, brand recognition, etc., to optimize the merchant's product loading and unloading process.
2. Responsible for e-commerce short video and livestream classification, multi-modal content mining, and multi-modal content understanding, optimizing e-commerce short video and livestream shopping experience.
3. Responsible for e-commerce image search, photo search goods, and goods duplication algorithm.
4. Explore the cutting-edge technology of computer vision and be responsible for the iteration and evolution of the overall algorithm and system.
5. Support the production of scalable and optimised AI/machine learning (ML) models.
6. Focus on building algorithms for the extraction, transformation, and loading of large volumes of real-time, unstructured data to deploy AI/ML solutions from theoretical data science models.
7. Run experiments to test the performance of deployed models and identify and resolve bugs that arise in the process.
8. Work in a team setting and apply knowledge of statistics, scripting, and programming languages required by the firm.
9. Work with the relevant software platforms on which the models are deployed.

Qualifications

1. Work experience in a university, industry, or government lab(s), in a role with primary emphasis on AI research.
2. Minimum 3 years of work experience in related fields.
3. In-depth research in a certain field of multimedia and computer vision, including but not limited to: image search, image/video classification and recognition, image segmentation, object detection, OCR, graph neural networks, multimodal, unsupervised and self-supervised learning, etc.
4. Familiar with the training and deployment of one or more framework models of TensorFlow/PyTorch/MXNet, and understand training acceleration methods such as hybrid precision training and distributed training.
5. Familiar with the latest research and technical progress of model compression acceleration, including but not limited to model quantization, pruning, knowledge distillation, etc., and inference frameworks such as TensorRT.

Preferred Qualifications

1. Strong practical ability; winners in Kaggle, COCO, ImageNet, ActivityNet, ICPC, NOI/IOI and other competitions are preferred.
2. Understanding AutoML related algorithms, network structure, or super parameter automatic search experience is preferred.
3. Familiar with big data related frameworks and application of MR/Spark is preferred.
4. Strong practical ability; papers published in relevant competitions and top academic conferences (such as CVPR, ICCV, ECCV, etc.) are preferred.