This role is part of the SCM Autonomation team at Coupang. As an ML Engineer, you will be at the forefront of developing and implementing machine learning models and pipelines that drive supply chain efficiencies and innovation. The ML Engineer is essential for building robust, scalable ML forecasting models and pipelines and ensuring their integration with SCM products to optimize inventory and supply chain processes end-to-end.
Location: Shanghai, China
What you will do
- Conduct and drive design and development of ML model engineering and pipelines for SCM related products focusing on demand forecasting for inventory optimization, and supply chain resilience.
- Design/Implement/Oversee the ML lifecycle, including data preprocessing, model training, evaluation, deployment, and monitoring.
- Collaborate with product managers to translate business requirements into scalable ML solutions, and work with a cross-functional team of Data Scientists, Data Analysts and Back-end Engineers to deliver world class ML solutions.
- Implement best practices for data management and model versioning to ensure reproducibility and compliance.
- As part of ML engineer team, foster a culture of innovation and continuous learning.
- Advocate for and apply advanced ML techniques and algorithms to forecast tens of millions of products/SKUs having complex demand patterns.
- Engage with stakeholders to demonstrate the business value of ML initiatives and gather feedback for continuous improvement.
- Stay abreast of the latest developments in ML and supply chain technologies to keep Coupang's SCM products at the cutting edge.
- Ensure the stability and performance of ML models in production, addressing any issues promptly and efficiently.
What are the 5 things we need this person MUST do/have?
- Proven expertise in developing and deploying ML models in a production environment and forecasting related domain experience is preferred.
- Strong proficiency with ML frameworks, tools, and languages such as Python, R, Java, TensorFlow, and PyTorch with demonstrated experience in distributed training of models to handle large-scale datasets
- Strong experience with Big Data ecosystem (Spark, Hive, HBase) and familiar with SQL and NoSQL (Redis/MongoDB)
- Excellent problem-solving skills with the ability to simplify complex concepts for a broad audience.
- Experience in conducting and driving ML projects, with a track record of delivering impactful ML solutions.
Essential Qualifications
- Minimum bachelor's degree in Computer Science, Engineering, or related field. A Master's or Ph.D. in Machine Learning, Data Science, or a related technical field is preferred.
- 8+ years of experience in machine learning engineering, with significant expertise in SCM or related fields.
