Job description

Responsibilities
1. Research on user behavior/preferences based on massive user data, and construct a user profile label system, such as demographic attribute labels, consumer labels, interest preference labels, and ID-mapping data
2. Improve and optimize the user portrait labeling system through machine learning/deep learning technology to increase label coverage
3. User life cycle management and optimization. Construct a user growth model to optimize the user life cycle. Such as new customer mining, conversion prediction, churn warning, etc.
4. Based on massive user data, it can provide strategic support for marketing orientation and improve the conversion rate of marketing activities
5. Link products and operations, analyze business data, provide reliable big data analysis and modeling solutions, and improve the product experience and business indicators
6. It can provide accurate feature engineering support for models such as CTR/CVR/LTV of the recommended algorithm to improve the model effect

Requirements
1. Bachelor degree or above in computer or related majors, with a solid foundation in mathematics, statistics, and computer
2. Familiar with user portrait (DMP) system construction, able to achieve accurate crowd orientation through user portrait modeling and other technologies
3. Master commonly used models such as machine learning/deep learning, be able to extract high-level portrait labels through algorithms and be able to predict and fill missing labels to improve user portrait label coverage
4. Proficiency in using at least one deep learning framework, such as TensorFlow, PyTorch, Caffe, etc.; proficient in at least one programming language, including but not limited to python/java/scala/go
5. Experience in recalling, rough sorting, and fine sorting in the recommendation/advertising field is preferred and can improve the model effect by digging into feature engineering
6. In-depth understanding of timing models, graph convolution models, NLP, CV, and other technologies is preferred [additional points]
7. Experience in big data frameworks is preferred, such as Hive, Spark, Flink, etc.

Please let the company know that you found this position on this Job Board as a way to support us, so we can keep posting cool jobs.