Machine Learning Engineer - Demand Forecasting (TikTok Global E-commerce Supply Chain and Logistics)

Data-E-commerce-Global Supply Chain and Logistics team: Our team is dedicated to enhancing clients' shopping experience and reducing operational costs in the supply chain and logistics of TikTok E-commerce by developing end-to-end algorithm capabilities using machine learning, operations research, data mining, and causal inference methods.

At TikTok, we are building a global e-commerce platform that connects millions of users with their favorite brands and products. Our Supply Chain and Logistics team plays a critical role in ensuring smooth operations and customer satisfaction. As a Machine Learning Engineer focused on demand forecasting, you will contribute to the development and implementation of cutting-edge machine learning models and algorithms to optimize inventory management, supply chain efficiency, and enhance the overall customer experience.

Role Overview

We are seeking a highly skilled and motivated Machine Learning Engineer with expertise in demand forecasting to join our dynamic and fast-paced team. In this role, you will collaborate with cross-functional teams including data scientists, engineers, product managers, and business stakeholders to develop innovative solutions that accurately forecast demand patterns and optimize inventory planning. Responsibilities: 1. Develop and implement end to end machine learning models and algorithms for demand forecasting in the context of TikTok's global e-commerce supply chain and logistics operations. 2. Collect, clean, and preprocess large-scale data sets to ensure data quality and suitability for forecasting purposes. 3. Collaborate with data scientists and domain experts to understand business requirements, identify key demand drivers, and incorporate relevant features into forecasting models. 4. Conduct exploratory data analysis to gain insights into demand patterns, trends, and seasonality factors that influence purchasing behavior. 5. Build scalable and efficient data pipelines to automate data preprocessing, model training, and prediction processes. 6. Evaluate and optimize the performance of existing time series forecasting models, and propose enhancements or alternative approaches to improve accuracy and robustness. 7. Collaborate with software engineers to integrate machine learning models into production systems and ensure reliable and timely delivery of forecasts. 8. Monitor model performance, identify anomalies, and develop proactive measures to address potential forecast errors or biases. 9. Stay up to date with the latest advancements in machine learning, demand forecasting techniques, and related domains, and apply this knowledge to enhance the team's capabilities. 10. Communicate findings, insights, and technical concepts effectively to both technical and non-technical stakeholders, fostering a collaborative and data-driven decision-making culture.