Machine Learning Engineer - Global E-Commerce - Personalized Presentation/Pricing & User Growth

Responsibilities

About Our Team
We are the core logistics algorithm team for global e-commerce, focusing on end-to-end logistics innovation and business implementation to address key pain points in pricing, cost, timeliness, and service quality through technology. In this role, you will be deeply involved in building core algorithmic frameworks. On one side, you will advance cutting-edge techniques such as deep learning, lead-time/ETA prediction, causal inference, and generative models to provide core algorithm support for platform growth. On the other side, you will connect key logistics factors with search/recommendation traffic ecosystems and the consumer conversion funnel, directly driving improvements in conversion and GMV. You will collaborate with top-tier toC/toB algorithm teams in the industry and grow both technically and in business impact through high-value, high-impact core scenarios.

Job Responsibilities
1. Design and implement algorithms for intelligent shipping-fee pricing, free-shipping strategy optimization, and subsidy-pricing coordination across diverse international e-commerce logistics scenarios. Build multi-objective pricing optimization models to balance user landed price, logistics cost, and business profitability, and deliver end-to-end cost reduction and efficiency improvement solutions.
2. Lead algorithm development for core businesses such as intelligent recommendation of logistics services and prediction of delayed user order conversions. Uncover how logistics factors influence consumer decision-making, build a measurable growth algorithm framework, and continuously improve platform conversion rate, repeat purchase rate, and GMV.
3. Develop a deep understanding of international e-commerce logistics scenarios. Through data mining and modeling, identify key levers for optimizing logistics operating models, cost control, and service quality. Leverage generative models to build ETA prediction and anomaly risk early-warning models, continuously improving user logistics experience.