About the job
You'll be joining the TikTok Recommendation team focusing on advancing large-scale recommender systems that power TikTok’s personalized content discovery and user experiences. By developing cutting-edge models, we aim to optimize recommendation accuracy, user engagement, and scalability across billions of users. We’re looking for Machine Learning Scientists passionate about building high-performance, scalable recommendation systems. You’ll leverage advanced deep learning techniques and large-scale systems engineering, collaborating with cross-functional teams to solve complex challenges in personalization and recommendation at scale.
Responsibilities
1. Research and develop large-scale recommender systems for personalized, engaging user experiences, focusing on scalability, accuracy, and performance.
2. Apply advanced machine learning and deep learning techniques to optimize recommendation algorithms for TikTok’s diverse user base.
3. Manage the end-to-end lifecycle of recommender models, from training and fine-tuning to deployment, monitoring, and continuous improvement.
4. Analyze complex data to uncover user preferences, behaviors, and trends, driving personalization and enhancing TikTok’s recommendation capabilities.
5. Collaborate with cross-functional teams (infrastructure, product, research, etc.) to design and implement innovative solutions that improve the relevance and diversity of TikTok recommendations.
Qualifications
Minimum
1. Individuals who are completing or have recently completed a PhD degree in Computer Science, Machine Learning, Artificial Intelligence, Statistics, or a related field.
2. Experience in one or more areas of recommender systems, machine learning, computer vision, or natural language processing.
3. Proficiency in programming skills, solid foundation in data structures and algorithms.
4. Strong familiarity with deep learning architectures such as transformers, CNNs, RNNs, LSTMs, etc.
5. Excellent analytical and problem-solving skills, with the ability to collaborate effectively in cross-functional teams.
Preferred
1. Experience in building large-scale recommender systems that handle vast, diverse datasets and complex user interactions.
2. Publications in major AI venues such as RecSys, SIGGRAPH, CVPR, ICCV, ICML, NeurIPS, ICLR, or similar conferences/journals.