Global E-commerce is a discovery-driven e-commerce business, working to become a destination for users to discover and buy good products at affordable prices.
We build a shopping experience that feels tailored to each user, and a platform merchants can rely on across live and short-video commerce.
The Supply Chain and Logistics team is a key pillar of that business, covering selection of goods, procurement, warehousing, and inventory management.
We improve the customer experience through warehousing, supply chain, and logistics technology, giving merchants dependable fulfillment so they can simplify and expand their business worldwide.
This means integrating digital systems with physical operations across warehouses, customs, transportation, and distribution networks, at high concurrency and with little margin for error at any step between seller and buyer.
You will build the systems that move real goods across borders, where a software decision shows up in a warehouse, a customs queue, and a delivery window.
Responsibilities:
1. Lead the adoption of state-of-the-art AI agent technologies across the data science workflow.
Design and productionize agentic solutions for data discovery, analysis, insight generation, decision support, and automated monitoring, with clear evaluation standards, guardrails, and human oversight.
2. Build intelligent insight and decision capabilities that proactively surface business and technical issues, recommend actions, and accelerate the cycle from opportunity identification through experimentation, iteration, and impact measurement.
3. Develop scalable analytics and modeling solutions for use cases, including demand and capacity forecasting, fulfillment and transportation optimization, merchant performance, network planning, anomaly detection, and simulation.
4. Use experimentation, causal inference, and rigorous measurement frameworks to evaluate logistics strategies, product changes, and operational programs;
clearly distinguish correlation from causal impact.
5. Partner with Product, Engineering, Operations, and business stakeholders to define high-value problems, establish success metrics, translate analyses into product or operational decisions, and drive solutions through implementation.
6. Create reusable data products, analytical frameworks, and self-service tools that improve the speed, consistency, and quality of decision-making across the organization.
7. Raise the technical bar for applied data science by establishing best practices in reproducibility, model and agent evaluation, monitoring, documentation, and responsible AI use.