Machine Learning Engineer (After-sales Experience) - TikTok E-commerce Governance

About the Team The E-commerce After-sales Algorithm Team is dedicated to building intelligent, fair, and efficient post-purchase service systems. We leverage advanced AI technologies to improve refund and return processing, dispute resolution, merchant responsibility attribution, customer service automation, and overall buyer experience. We focus on balancing user experience, merchant ecosystem health, and platform risk control, ensuring sustainable e-commerce growth.

Responsibilities

• Develop and optimize machine learning / deep learning models for after-sales scenarios such as refunds, returns, cancellations, disputes, and compensation.
• Build intelligent decision-making systems for responsibility attribution and dispute resolution between buyers and sellers.
• Develop NLP and multimodal models to analyze customer service conversations, complaint texts, product descriptions, and evidence materials.
• Build predictive models to proactively identify high-risk transactions and reduce after-sales disputes.
• Optimize real-time and offline feature engineering pipelines for large-scale transactional and behavioral data.
• Design and run A/B experiments to improve resolution efficiency, fairness, and user satisfaction.
• Collaborate closely with product, operations, and engineering teams to translate algorithmic capabilities into scalable production systems.

Minimum Qualifications

• Bachelor’s degree or above in Computer Science, Statistics, Mathematics, or related fields.
• At least 1 year of experience in machine learning, recommendation systems, risk control, or related algorithm domains.
• Solid understanding of machine learning and deep learning fundamentals, with hands-on project experience.
• Experience in one or more of the following areas: Data Mining, NLP, Graph Learning, Risk Modeling.
• Proficient in Python and familiar with at least one of Go/C++ under Linux development environment.
• Strong analytical thinking and problem-solving skills, with a data-driven mindset.
• Good communication skills and strong teamwork spirit.

Preferred Qualifications

• Experience in e-commerce after-sales, payment risk control, fraud detection, or customer service intelligence.
• Experience designing responsibility attribution or decision systems under fairness constraints.
• Experience deploying the LLM-based responsibility attribution agent.
• Publications in top conferences (e.g., KDD, WWW, NeurIPS, ACL) or awards in international competitions.