Machine Learning Engineer, E-Commerce Risk Control - USDS Seattle Regular R&D : A148522

Machine Learning Engineer, E-Commerce Risk Control - USDS

Seattle Regular R&D Job : A148522

About the team

The E-Commerce Risk Control team works to minimize the damage of inauthentic behaviors on Tiktok E-Commerce platforms, covering multiple classical and novel business risk areas such as account integrity, incentive abuse, malicious behaviors, brushing, click-farm, information leakage, etc. In this team you'll have a unique opportunity to have first-hand exposure to the strategy of the company in key security initiatives, especially in building scalable and robust, intelligent and privacy-safe, secure and product-friendly systems and solutions.

Our challenges are not some regular day-to-day technical puzzles - You'll be part of a team that's developing novel solutions to first-seen challenges of a non-stop evolution of a phenomenal product eco-system. The work needs to be fast, transferable, while still down to the ground to make quick and solid differences.

Responsibilities

• Invent, implement, and deploy state-of-the-art machine learning algorithms, build prototypes, and explore entirely new conceptual solutions to address and mitigate business risks in Tik Tok e-commerce/platforms, including but not limited to fraudulent merchants, cheating influencers, malicious users, information security issues, and cross-domain risk challenges.
• Utilize techniques such as representation learning, graph models, deep learning, transfer learning, and multi-task learning to improve the efficiency of problem detection, enabling rapid risk mitigation and optimizing various metrics of the e-commerce community ecosystem.
• Monitor and attribute key metrics to promptly perceive changes in risk and business, proactively identify potential attacks, continuously optimize and adjust risk control strategies, and drive the development of risk governance and business model adjustments.
• Mine and analyze massive e-commerce content and user behavior data to build both short-term and long-term user profiles, improving model accuracy and recall, as well as enhancing robustness, automation, and generalization capabilities.
• Advance risk machine learning capabilities in privacy/compliance, interpretability, risk perception, and analysis; innovate models and algorithms tailored to the characteristics of content e-commerce, building an industry-leading content e-commerce risk control algorithm system.

Qualifications

• Minimum Qualifications
  - Master’s degree in Computer Science, Mathematics, Machine Learning, or other relevant STEM fields.
• 1+ years of hands-on experience building and delivering machine learning models for large-scale projects in internet companies.
• Proficient in C++/Java/Python with strong coding skills, and familiarity with at least one common machine learning/deep learning platform.
• Experience in e-commerce/internet companies in fraud or risk control roles, with a track record of building fraud detection, anomaly detection, or other risk control models using relevant algorithms.
• Strong critical, objective, and thinking skills; able to reason and communicate in a results-oriented, data-driven manner with high autonomy.

• Preferred Qualifications
  - PhD in Computer Science, Machine Learning, Statistics, Operations Research, or related fields.
• 5+ years of hands-on experience in building and delivering large-scale risk control projects in internet/e-commerce companies, with proven success in large-scale anti-fraud data mining; strong coding (backend, infrastructure, algorithms) and system design skills.
• Strong technical leadership combined with hands-on data mining and machine learning expertise; passionate about tackling Tik Tok’s data scale and business complexity; able to identify, plan, and lead both quick-win tactics and…