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 the most 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 to give video search a more powerful retrieval capability 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 understand you better 4. Architecture with hundreds of billions of data scale: In-depth research and innovation in all aspects from large-scale offline computing, distributed system performance and scheduling optimization to building high-availability, high-throughput and low-latency online services. 1. Participate in the improvement of the core algorithm of Douyin search: use the most advanced NLP, CV, CTR estimation and other technologies to continuously improve the accuracy of search results and continuously improve the user's search experience 2. Possible directions include: 1) Matching technology (text matching and multi-mode matching): Matching technology is the core of search engines. In Douyin search, you will have the opportunity to apply cutting-edge NLP and CV technologies to match the most relevant videos for each query, and continue to improve the relevance of Douyin search 2) Click-through rate estimation: Solve the recommendation problem in search, so that Douyin search can add personalized capabilities on the basis of relevance and better understand users 3) Video understanding: Comprehensive use of NLP, CV, graph neural network and other technologies to understand videos from the perspective of the video itself and social networks, improving the authority, credibility and usefulness of search results 4) New product forms and technologies: Explore efficient and convenient interactive technologies such as smart covers, video summaries, and precise video Q&A.
Qualifications
1. Excellent problem analysis and problem-solving abilities 2. Excellent basic capabilities of machine learning and deep learning. , have certain application experience in NLP, CV, CTR prediction, graph neural network, etc. 3. Strong coding ability, data structure and basic algorithm skills 4. Familiar with Linux development environment, proficient in using C++ and Python languages 5. Bonus points for those with experience in search algorithms.
