Job Description

Requirements

Proficiency in Python and PySpark for data analysis, machine learning, and demand forecasting (regression + time series models)
Experience with forecasting models such as LightGBM/ XGBoost and classical time series methods (e.g., ETS/ARIMA)
Strong understanding of the machine learning workflow (data cleansing, feature engineering, model evaluation, model explainability)
Familiarity with forecasting evaluation metrics (e.g. MAPE, MAE) and ability to validate model performance
Strong SQL skills for managing and querying large datasets
Knowledge of data visualization tools (e.g., Power BI)
Experience with cloud-based technologies such as Databricks, Azure, or AWS
Strong communication skills — able to explain insights and models to both business and technical teams
Ownership and accountability — able to deliver end-to-end solutions, not just analysis
Collaboration — able to work effectively with Data Engineering, Tech, Product, and Supply Chain teams

Preferred (Optional) Qualifications

Exposure to MLOps tools (e.g., MLflow, job scheduling)
Experience building production pipelines for forecast outputs (daily/weekly runs) and supporting downstream systems
Experience in real-time analytics or scheduled processing systems
Optimization mindset — able to balance accuracy, business impact, and time constraints

Benefits