Machine Learning Engineer Graduate (Data-Global E-Commerce-Search) - 2027 Start (PhD)

The Search E-Commerce team spearheads the development of TikTok's advanced search algorithm, crucial for its booming global e-commerce platform. Utilizing state-of-the-art large-scale machine learning, along with cutting-edge NLP, CV, and multi-modal technologies, we are committed to creating a top-tier search engine. Our goal is to deliver the best e-commerce search experience to over a billion monthly TikTok users worldwide. Our mission is to create a world where "no reasonably priced product is difficult to sell."

We are looking for talented individuals to join our team. As a graduate, you will get opportunities to pursue bold ideas, tackle complex challenges, and unlock limitless growth. Successful candidates must be able to commit to an onboarding date by the end of the year. Please state your availability and graduation date clearly in your resume.

This full-time PhD Graduate role provides early-career researchers and engineers the opportunity to join one of our engineering teams where you will have the opportunity to: Participate in applied research and improvement of the search core algorithm, possible directions include: - Content understanding: Applying the industry's cutting-edge NLP and CV technology and leveraging LLM to match the most relevant videos for each search query, and continuously improve the relevance of TikTok search. - User Behavior Modeling: solving the recommendation problem in search, let TikTok search increase the ability of personalization on the basis of "relevant", and understand users better. - Video understanding: comprehensive use of NLP, CV, as well as LLM for better video understanding from the perspective of the video itself and social network, improve authority, credibility, and usefulness of search results. - Search research and evaluation: developing new retrieval, ranking, relevance evaluation, query understanding, multimodal search, or LLM application methods and translating research ideas into scalable product improvements.