Description

You will own the development and operationalization of advanced forecasting and anomaly detection systems.

Responsibilities

• Build, train, and deploy time-series forecasting models using XGBoost, Random Forest, Linear regression, ARIMA, SARIMA, Holt-Winters, or Prophet.
• Operationalize model pipelines using GCP services (BigQuery, Cloud Composer, DataProc, Cloud Run) or equivalent cloud platforms.
• Develop scalable data processing workflows using Python, PySpark, and SQL to handle large datasets.
• Design and implement data anomaly detection systems and build automated alerting frameworks for forecast issues.
• Develop and maintain accuracy measurement frameworks (MAPE, RMSE, MAE, WAPE, Bias) and communicate performance trends to stakeholders.

Required Skills

• 5+ years of experience as a Data Scientist with hands-on model development.
• Strong programming skills in Python, including PySpark and Pandas/NumPy.
• Expertise with time-series forecasting, regression models, and ensemble methods.
• Proficiency in SQL and experience working with large-scale datasets.
• Hands-on experience with GCP, AWS, or Azure cloud environments.
• Ability to diagnose data issues, perform anomaly analysis, and build automated alerting solutions.
• Strong domain knowledge in retail supply chain, inventory planning, or demand forecasting.

Key Skills

Education

Any Graduate