Machine Learning Engineer(NLP/CV/Multimodal), TikTok E-commerce Knowledge Graph
Core
Developing state-of-the-art NLP/ML algorithms and strategies to build product knowledge graphs for TikTok's global e-commerce business, supporting feed ranking, recommendations, and ads.
Role type
Senior IC machine learning engineer (NLP/CV/Multimodal)
Builds
Massive knowledge graphs of real-world products, buyers, and content
Domain
E-commerce, Knowledge Graphs, NLP, Computer Vision
Deliverable
production ML models
Required skills
Machine learning, NLP, multimodal learning, computer vision, software development (C++, Python, Go, Java), knowledge graph construction, product/content/feedback understanding, category/brand/SPU construction, buyer-product graph construction
Preferred skills
Deep learning frameworks (TensorFlow/PyTorch), distributed training, distillation acceleration, text classification, text matching, sequence labeling, domain adaptation, small sample construction, text mining, unsupervised/semi-supervised learning, large-scale data processing (Hadoop/Spark/Hive/Flink), model tuning, text representation methods (LDA/Word2Vec/ELMo/GPT/BERT)
Responsibilities
Participate in the development of massive knowledge graphs of real-world products to support feed ranking, recommendations, and ads; Collaborate with product managers, data scientists, and the product strategy & operation team to define product strategies and features; Construct knowledge graphs of buyers and products
Seniority
Mid-Senior, hands-on IC
