CV/NLP/Multi-mode Dynamic Algorithm Engineer

Responsibilities

Team introduction: The platform governance algorithm team was established in September 2020. Its main responsibility is to optimize the algorithm and cooperate with the e-commerce business team to conduct a comprehensive quality/ecological review of ByteDance e-commerce products. Governance includes not only cracking down on low-quality/risk/violation issues, but also including style optimization, high-quality content support, e-commerce ecological construction, etc. The mission of the platform governance algorithm team: guaranteed operation and delivery, and everything you see and get is good Vision: to create a safe and compliant platform order and establish a healthy ecosystem trusted by users. 1. Responsible for using algorithms to mine, identify and predict risks and low-quality merchants/commodities/hosts in e-commerce scenarios, and cooperate with business management and control 2. Responsible for using algorithms to mine events and events that affect product experience and contract fulfillment timeliness experience. Behavior, build data models, assist in building a good ecological experience environment, and provide support for business 3. Participate in building and mining data of various entities such as e-commerce live broadcasts, products, merchants, and anchors carrying goods, and analyze large-scale networks/massive feature sequences Carry out modeling to support content understanding/multimodal representation/community mining and other business scenarios to solve problems, and provide support for product/live broadcast/video governance 4. Participate in building a large-scale graph storage and graph learning platform to improve the e-commerce community Build relationships with internal merchants/commodities/cargo anchors, and empower and manage business 5. Explore and investigate cutting-edge technologies in machine learning/graph learning/sequence learning and related directions, and implement them in real business scenarios.

Qualifications

1. Have solid coding skills and be familiar with deep learning/graph neural network/machine learning frameworks, such as pytorch, tensorflow, DGL, pyg, sklearn, etc. 2. Familiar with one or more of machine learning/graph learning/sequence learning algorithms, such as graph modeling, time series signal modeling, node/subgraph classification, community mining, representation learning, self-supervision/ Semi-supervised learning, etc., with a certain depth and breadth 3. Applicants who are familiar with the application of relevant algorithms in data mining, search recommendation, content understanding, governance and risk control are preferred 4. Proficient in using numpy, pandas, etc. to independently conduct modeling experiments, familiar with large-scale Priority will be given to those with data tools Hive, Spark, and Hadoop 5. Publishers of articles at top conferences in the fields of data mining, machine learning (KDD, ICML, NIPS, VLDB, etc.), or winners of data mining competitions (Kaggle, Tianchi) will be given priority .