Binance Accelerator Program - Search & Recommendation Data scientist

Assist senior algorithm engineers in the design and daily maintenance of search and recommendation services and models in content scenarios, support the content team and empower the development and iteration of the content ecosystem.

Support the optimization of content matching accuracy and distribution efficiency by applying machine learning-based personalization methods, common design patterns and tools, and participate in basic model tuning and effect verification.

Learn and understand the core logic of recommendation systems in the content domain, assist in the iteration of AI products to improve user content experience and core business metrics.

Participate in the auxiliary development and implementation of core content recommendation modules, assist in implementing data-driven strategies to maximize content value and user engagement.

Collaborate with content, business and product teams to identify needs and opportunities in content scenarios, and assist the team in defining core success metrics.

Currently pursuing a Bachelor's, Master's or PhD degree in Machine Learning, Computer Vision, Computer Science, Applied Mathematics, Data Science or related disciplines.

Solid programming foundation, proficient in Python, familiar with at least one mainstream machine learning framework, and grasp basic machine learning algorithm theories.

Basic understanding of search and recommendation system fundamentals; relevant coursework, competition experience or campus project experience is preferred.

Basic proficiency in SQL for large-scale data cleaning and feature engineering support, with strong hands-on ability.

Clear logical thinking, strong quick-learning ability, excellent cross-team communication skills, able to commit to at least 6 months full-time internship.

Preferred Qualifications: Publication record or submission at top-tier conferences/journals, relevant internship experience in search & recommendation, experience in content-related recommendation system projects.