Responsibilities
Team introduction: ByteDance's Douyin search team is mainly responsible for Douyin search algorithm innovation and architecture research and development, mainly including short video, live broadcast, local life, visual search and other business lines. We use the most cutting-edge machine learning technology for end-to-end modeling and continue to innovate and make breakthroughs. At the same time, we focus on the construction and performance optimization of distributed systems and machine learning systems, from memory and disk optimization to the exploration of index compression, recall, sorting and other algorithms, fully providing students with opportunities to grow themselves. The main work directions include: 1. Exploring cutting-edge NLP technology: from basic word segmentation, NER, to application Query analysis, basic correlation, etc., applying deep learning models in the entire link, every detail is full of challenges 2. Cross-modal matching technology: applying CV+NLP deep learning technology in search, allowing video search Search has more powerful retrieval capabilities 3. Large-scale streaming machine learning technology: Apply large-scale machine learning to solve the recommendation problem in search, making the search more personalized and understanding of you 4. Architecture with hundreds of billions of data scale: from large-scale offline computing, performance and scheduling optimization of distributed systems, to building high availability, high throughput and low... In-depth research and innovation go into every aspect of our online services. 1. Participate in search engine research and development, explore personalized behavior modeling of the entire search link (analysis, recall, rough ranking, fine ranking, mixed ranking), including CTR, CVR estimation, vector recall, value mixing, RAG, NLP, LLM, multi-modality, machine learning, deep learning, etc., promote the implementation and improvement of search algorithms in international e-commerce scenarios, and improve the search experience of hundreds of millions of users 2. Participate in the optimization and iteration of international e-commerce search algorithms to improve conversion efficiency, user experience and supply ecology solve technical problems such as multi-language relevance matching, authoritative perception, understanding of seed content, repeated distribution of goods, and control of counterfeit goods, and optimize the basic search quality of various e-commerce business forms such as content e-commerce and traditional shelf e-commerce extremely improve the shopping conversion efficiency of products, seed videos and live broadcasts with goods, and promote GMV growth 3. In-depth participation in the demand design of core search products, responsible for the high-quality delivery of algorithms and projects, and continuous optimization of results to improve product experience 4. Mining data, building Query understanding, recall, sorting and other models to improve e-commerce search algorithm capabilities 5. Learning cutting-edge technologies and exploring the implementation of innovative technologies such as large models in AI search scenarios.
Qualifications
1. Bachelor degree or above, computer, electronics, mathematics and other related majors 2. Priority will be given to those who have in-depth researchers in one or more fields such as search, recommendation, search promotion, computer vision CV, natural language processing NLP, natural language understanding NLU, multi-modality, machine learning, deep learning, etc. 3. Familiar with the Linux development environment, skilled in the use of C++ and Python languages, familiar with Html and related technologies, and familiar with network programming will be preferred 4. Have good problem analysis and solving skills, communication and collaboration skills, be proactive in work, and be able to work harmoniously with the team to explore new technologies and promote technological progress. Bonus points: 1. Those with excellent basic algorithms, solid machine learning/deep learning foundation, familiar with technologies in CV, NLP, RL, ML and other fields, priority will be given to those who have published papers in top conferences/journals such as ICML, ACL, COML, EMNLP, CVPR, ECCV, ICCV, NeurIPS, ICLR, SIGGRAPH or SIGGRAPH Asia 2. Applicants with excellent coding skills, proficient in C/C++ or Python programming language, winners of ACM/ICPC, NOI/IOl, Top Coder, Kaggle and other competitions are preferred 3. Applicants who have led projects with large impact in the fields of LLM, multimodality, large models, basic models, world models, RL, etc. are preferred 4. Applicants with relevant experience in large-scale search engines, recommendation systems, distributed systems, computational advertising, ultra-large-scale data calculations, etc. are preferred.
