Staff Data Scientist-SCM Autonomation
Coupang is the largest e-commerce company in Korea, delivering millions of items, including fresh groceries, within hours to millions of people, 365 days a year. Our mission is to create a world in which customers wonder, ‘How did I ever live without Coupang?’ Korea is one of the fastest growing e-commerce markets in the world, and Coupang is a leader in this fast-growing industry. Powered by innovative technology and operations, we have set out to transform the customer experience journey–from revolutionizing last-mile delivery to rethinking how customers search and discover on a truly mobile platform. We have invested heavily in infrastructure and technology, building an integrated system that we control from end to end. This enables us to improve as we grow, build new services, and break the tradeoffs between price, selection, and quality that consumers are too often forced to take for granted.
We have been named as one of the ‘50 Smartest Companies in the World’ by MIT Technology Review, and as one of Forbes magazine’s ‘30 Global Game Changers.’ In 2020, we placed second on CNBC’s ‘Disruptor 50’ list.
Who We Are?
The Supply Chain Data Science team is responsible for predicting what customers want to buy and automate the ordering process. We create a daily demand forecast for all Coupang’s Retail SKUs, every day. We work with internal stakeholders to solve challenging Supply Chain problems at scale. Our systems ensure Coupang’s customers are delighted with consistently available products. Automation supports scale and efficiency of our Supply Chain processes.
How We Do It?
We use Machine Learning/Deep Learning processes to generate our daily forecast and buying decisions. We focus on Time Series models for predicting customer demand. We provide the Data Science team with Data Engineering, Software Engineer and Data Analysis resources to ensure the Data Science team can focus on building the best models. Our goal is to apply cutting edge models into our production environment, using a deep understanding of the e-commerce business domain to demonstrate results in production. We join big thinking with a pragmatic approach to measuring results.
Our systems are built on Hadoop and Spark, with forecasting models implemented in Python using SciPy, NumPy, etc. Our Automated Buying systems combine machine learning with human oversight. Data Scientists work with a cross-functional team of Engineers, Analysts and Product Owners to build world-class systems that keep our Supply Chain running smoothly.
- Design and implement models to predict customer demand, recommend supplier order quantities and make inventory management recommendations
- Develop model evaluation criteria and accuracy KPIs
- Collaborate with engineering teams to launch models into production
- Provide requirements and use cases for Big Data infrastructure
- Explore new Machine Learning/Deep Learning applications to Time Series prediction
- Mentor junior data scientists / analysts and provide career development advice
- 3-5 years relevant experience;
- Masters in Mathematics, Statistics, Econometrics, CS or Engineering;
- Ph. D. a plus
- Expertise in R or Python
- Experience with Time Series prediction (Regression, ARIMA, GLM, LSTM, etc)
- Practical Machine Learning experience (Data Preprocessing, Feature Selection / Engineering, Training, Model Evaluation)
- Experience with Deep Learning (NLP, CV, etc.) practices in business scenarios a plus
- Working experience with Python ML libraries (SciKit, Pandas) a plus
- Working experience with Scala or Java a plus
- Experience with big data ecosystem (Spark, Hive, Pig, Sqoop, Oozie) a plus
- Supply Chain domain experience a plus