Staff Data Scientist (SCM Autonomation)

We exist to wow our customers. We know we’re doing the right thing when we hear our customers say, “How did I ever live without Coupang?” Born out of an obsession to make shopping, eating, and living easier than ever, we’re collectively disrupting the multi-billion-dollar commerce industry. We are one of the fastest-growing retail companies that established an unparalleled reputation for being a leading and reliable force in the commerce industry.

We are proud to have the best of both worlds — a startup culture with the resources of a large global public company. This fuels us to continue our growth and launch new services at the speed we have been since our inception. At Coupang, every day is filled with the excitement of building, you will see yourself, your colleagues, your team, and the company grow every day.

Our mission to build the future of commerce is real. We push the boundaries of what’s possible to solve problems and challenge traditional tradeoffs. Join Coupang now to create an epic impact in this always-on, high-tech, and hyper-connected world.

Role Overview

This role would be part of SCM Autonomation team in Coupang supporting fast growing Taiwan ecommerce business. SCM Autonomation team is responsible for building products, deep data science capabilities, analytical frameworks and owning processes end to end to provide world class solutions to our customers. Robust Forecasting platform with SOTA ML/DL models and system capabilities is one of core solution owned by this team. Forecasting is holy grail for any retail company affecting both growth and health of the organization. With compute constraint out of equation, ML/DL forecasting models influence SKUs availability to customers significantly and that’s again at right cost.

This role will involve building forecasting SOTA ML/DL models solving complex business use cases aside promotion, seasonal, cyclicity, long horizon forecasting. The person is expected to understand deep data science model nuances, bring complete visibility & control on ML/DL model design, trade-offs taken and influence stakeholders around to take right prioritization decisions. The person is also expected to problem solve non-forecasting related data science use cases on classification, regression and clustering areas.

What You Will Do

• Define machine learning models and establish a demand forecasting model roadmap: Establish a forecasting model strategy covering various business lines such as Fresh and Core
• Feature Engineering: Both automated and business-context driven model features that reflect both horizontal common requirements and vertical domain-specific requirements.
• Design and implementation of data preprocessing algorithms
• Developing ML/DL models with relevant experiment design, model architecture and validation/evaluation techniques
• Collaborate with product, business, finance, and analytics teams to prioritize features
• Provides clear structure and explanation for ML model design
• Eliminate fundamental flaws through in-depth analysis of model operation
• Improving the quality, visibility, and transparency of model input data
• Build processes and technology solutions that continuously monitor and validate predictive model inputs to ensures model accuracy and relevance over time
• Thorough input data management to prevent “Garbage In, Garbage Out”

Qualifications

• Minimum Master's degree or higher
• 8-12 years of experience in data science and modelin
• Excellent analytical thinking skills and Excel/SQL proficiency
• Data science experience: Experiment designing and building ML/DL models from scratch
• Excellent data analysis and modeling skills, ability to use Python or R
• Product Documentation (PRD), Visualization, and Simulation Capabilities: Ability to create documents and materials that effectively support decision making
• Prioritization and multitasking skills: Ability to clearly identify and pursue key tasks while working on multiple projects simultaneously