Recommendation Algorithm Engineer-TikTok Algorithm-Soaring Star Talent Program

Overview Recommendation Algorithm Engineer-TikTok Algorithm-Soaring Star Talent Program is a role at ByteDance. Join to apply for the Recommendation Algorithm Engineer-TikTok Algorithm-Soaring Star Talent Program role at ByteDance . 2 days ago Be among the first 25 applicants. Responsibilities Team Introduction: Research & Development (R&D) Team. The R&D team is dedicated to building and maintaining industry-leading products that drive the success of global business. You will work on core scenarios such as user growth, social features, live streaming, e-commerce consumer side, content creation, and content consumption, helping our products scale rapidly across global markets. You will face technical challenges in areas like service architecture and infrastructure engineering, ensuring systems operate with high quality, efficiency, and security. The team provides comprehensive technical solutions across diverse business needs, continuously optimizing product metrics and improving user experience. You will collaborate with leading experts and work on cutting-edge technologies to push the boundaries of what’s possible. Your code will serve hundreds of millions of users, in an egalitarian and easy-going collaborative environment. We welcome you to join us and make a global impact with ByteDance. Research Project Introduction: ByteDance faces challenges in its recommendation systems, including data sparsity for new users, high timeliness requirements for live streaming recommendations, maintaining user interest diversity, and the complexity of e-commerce recommendation chains. Traditional methods rely on historical behavior modeling and can struggle with cold-start problems. Live-streaming recommendations require real-time responsiveness to rapidly changing content dynamics within short time windows. The single-feed format amplifies the need to balance multi-interest learning with avoiding content drift. The current e-commerce system uses a multi-stage funnel (recall–ranking–re-ranking) which can lead to inconsistent chains and high maintenance costs. The project proposes leveraging large language models (LLMs), graph neural networks (GNNs), and full-lifecycle user behavior sequences to improve prediction accuracy and model social preferences, aiming to simplify chains, enhance real-time adaptability, and improve exploratory recommendations. The ultimate goal is a streamlined system with more accurate recommendations that enhances user experience and drives sustainable business growth. Qualifications PhD degree preferred in Artificial Intelligence, Computer Science, Mathematics, or related fields. Strong programming skills with solid software design ability and coding practices. Outstanding problem-solving and analytical skills, passion for technology, and strong communication and teamwork. Familiar with machine learning, natural language processing, and/or data mining. Prior experience in recommendation systems, computational advertising, or search engines is a plus. About Us Founded in 2012, ByteDance’s mission is to inspire creativity and enrich life. With products including TikTok, Lemon8, CapCut, Pico, Toutiao, Douyin, and Xigua, ByteDance connects people to create and enjoy content. Why Join ByteDance: We aim to inspire creativity and enrich life. Our teams are diverse and collaborative, focused on meaningful breakthroughs and ongoing innovation. We strive for a culture of curiosity, humility, and impact, operating with an "Always Day 1" mindset. Diversity & Inclusion: ByteDance is committed to an inclusive workplace where employees are valued for their skills, experiences, and perspectives. We celebrate diverse voices and create an environment that reflects the communities we reach. Job Details Seniority level Internship Employment type Full-time Job function Engineering and Information Technology Industries Software Development Referrals increase your chances of interviewing at ByteDance by 2x. Get notified about new Algorithm Engineer jobs in Singapore . #J-18808-Ljbffr