TikTok is the leading destination for short-form mobile video. Our mission is to inspire creativity and bring joy. U.S. Data Security (“USDS”) is a subsidiary of TikTok in the U.S. This new, security-first division was created to bring heightened focus and governance to our data protection policies and content assurance protocols to keep U.S. users safe. Our focus is on providing oversight and protection of the TikTok platform and U.S. user data, so millions of Americans can continue turning to TikTok to learn something new, earn a living, express themselves creatively, or be entertained. The teams within USDS that deliver on this commitment daily span across Trust & Safety, Security & Privacy, Engineering, User & Product Ops, Corporate Functions and more.

Why Join Us
Creation is the core of TikTok's purpose. Our platform is built to help imaginations thrive. This is doubly true of the teams that make TikTok possible.
Together, we inspire creativity and bring joy - a mission we all believe in and aim towards achieving every day.
To us, every challenge, no matter how difficult, is an opportunity; to learn, to innovate, and to grow as one team. Status quo? Never. Courage? Always.
At TikTok, we create together and grow together. That's how we drive impact - for ourselves, our company, and the communities we serve.
Join us.

About the Team
The Governance and Experience Algorithm team was established in September 2020 and its main job is to support the following businesses with the most advanced AI technology：
- Combat any kinds of risks/violations issues in E-commerce scenarios.
- Build a healthy E-commerce ecosystem and improve platform service capabilities

Responsibilities:
- identifying algorithms for risk/violation/low-quality issues in e-commerce scenarios such as products, shopping cart short videos, and live streaming with products.
- mining and identifying algorithms to detect fraudulent behaviors and identify risky, violated, or low-quality merchants and creators.
- optimizing algorithms for large-scale brand libraries, products, and content deduplication/clustering.
- data construction, instruction fine-tuning, CoT, alignment, and other work for large models in the e-commerce domain, aiming for ultimate effect optimization in the e-commerce domain.
- exploring reinforcement learning and operational research algorithms in intelligent dispatching and intelligent audit scheduling to improve audit quality and efficiency.

What You Will Do:
- Optimize various basic algorithms such as NLP, vision, multimodal, search, graph, LLM, etc. to provide support for governance business, explore cutting-edge technologies, and apply them to e-commerce business scenarios.
- Streamline the optimization and iteration process for computer vision models in e-commerce settings, including fine-grained classification of product images, product object recognition, product subject recognition, feature extraction, logo detection, brand recognition, etc.
- Optimize video classification, multimodal content mining, and multimodal content understanding of e-commerce short videos and live broadcasts, and optimize the e-commerce short video shopping experience.
- Optimize the risk identification model related to text content in e-commerce scenarios, such as product copywriting, picture text, and voice descriptions.
- Optimize the risk mining algorithm for comments, reports, and other public opinion content related to products/short videos/live broadcasts, and improve the platform governance effect.
- Responsible for the research of large-scale multimodal (vision, speech, natural language, etc.) algorithms and their implementation in e-commerce scenarios.
- Extract extensive data from various entities, such as content in e-commerce live broadcasts, products, merchants, and influencers.

In order to enhance collaboration and cross-functional partnerships, among other things, at this time, our organization follows a hybrid work schedule that requires employees to work in the office 3 days a week, or as directed by their manager/department. We regularly review our hybrid work model, and the specific requirements may change at any time.