TikTok E-Commerce platforms are facing inauthentic behaviors such as account integrity, incentive abuse, malicious behaviors, brushing, click-farm, information leakage, etc., and the company needs to minimize the damage of these risks.
Requirements
- Proficiency in C++/Java/Python with strong coding skills, and familiarity with at least one common machine learning/deep learning platform.
- Deep understanding of supervised learning, unsupervised learning, and deep learning techniques, and the ability to build business algorithm models using relevant algorithms.
- Experience with machine learning algorithms such as representation learning, graph models, deep learning, transfer learning, and multi-task learning.
- Familiarity with data mining and analysis techniques, and the ability to work with large datasets.
- Ability to keep up with and proactively apply relevant technological advancements, incorporating the latest technologies (e.g., LLM, Multi-agent systems) into daily work.
Responsibilities
- Invent, implement, and deploy cutting-edge machine learning algorithms, build prototypes, and explore entirely new conceptual solutions to respond to and mitigate business risks in TikTok e-commerce/platforms, including but not limited to fraudulent merchants, cheating influencers, malicious users, information security issues, and cross-domain risk challenges.
- Leverage techniques such as representation learning, graph models, deep learning, transfer learning, and multi-task learning to improve the efficiency of problem detection, thereby rapidly blocking risks and optimizing various metrics in the e-commerce community ecosystem.
- Monitor and attribute key metrics to quickly detect changes in risk and business trends, proactively identify potential attacks, continuously refine and adjust risk control strategies, and drive risk governance development and business model improvements.
- Mine and analyze massive e-commerce content and user behavior data to build both short-term and long-term user profiles, improve model precision and recall, and enhance robustness, automation, and generalization capabilities.
- Advance risk ML capabilities in privacy/compliance, interpretability, risk perception, and analysis; innovate models and algorithms tailored to the characteristics of content e-commerce, and build an industry-leading content e-commerce risk control algorithm system.
Other
- Master’s degree in Computer Science, Mathematics, Machine Learning, or other relevant STEM disciplines.
- 2+ years of hands-on experience in building and delivering machine learning models for large-scale projects in internet companies.
- Ability to think critically, objectively; reason and communicate in a results-oriented, data-driven manner; and work with high autonomy.
- Hybrid work schedule that requires employees to work in the office 3 days a week, or as directed by their manager/department.
- Ability to work with and support systems designed to protect sensitive data and information, and subject to strict national security-related screening.
