Job Description: We are seeking a highly skilled Senior Data Scientist with strong experience in cloud-based data platforms (Google Cloud or similar), Python/PySpark development, and advanced time-series forecasting. The ideal candidate will have deep supply chain domain expertise—preferably in Demand Forecasting—and a proven track record of building, training, and operationalizing predictive models at scale. This role will also focus on identifying data anomalies, creating alerting frameworks, and improving model accuracy through metric evaluation and tuning.

Key Responsibilities:

Model Development & Forecasting
•    Build, train, and deploy time-series forecasting models using techniques such as:
o    XGBoost
o    Random Forest
o    Linear regression–based models
o    ARIMA, SARIMA, Holt-Winters
o    Prophet / FBProphet
•    Operationalize model pipelines using Google Cloud Platform (GCP) services (BigQuery, Cloud Composer, Dataproc, Cloud Run) or equivalent cloud technologies (AWS, Azure).
•    Perform feature engineering, hyperparameter tuning, model validation, and continuous improvement of forecasting pipelines.
Data Engineering & Cloud Expertise
•    Develop scalable data processing workflows using Python, PySpark, and SQL.
•    Work with large datasets and cloud-native data environments for analytics and modeling.
•    Collaborate with data engineering teams to ensure robust data pipelines and high-quality training data.
Analytics & Anomaly Detection
•    Design and implement data anomaly detection systems to identify volume, pattern, and trend deviations.
•    Build automated alerting frameworks for early warning of data or forecast issues.
•    Investigate root causes of anomalies and recommend long term fixes.
Accuracy Metrics & Optimization
•    Develop and maintain accuracy measurement frameworks (e.g., MAPE, RMSE, MAE, WAPE, Bias).
•    Continuously fine tune and optimize model performance based on metric evaluations.
•    Communicate model accuracy trends and insights to both technical and business stakeholders.
Domain Expertise – Supply Chain & Demand Forecasting
•    Apply strong domain knowledge in retail supply chain, inventory planning, replenishment, and demand forecasting.
•    Partner with business teams to translate forecasting needs into data science solutions.

Required Qualifications
•    Bachelor’s or Master’s degree in Data Science, Computer Science, Statistics, Mathematics, or a related field.
•    5+ years of experience as a Data Scientist with hands-on model development.
•    Strong programming skills in Python, including PySpark and common data science libraries (Pandas, NumPy, SciPy, scikit learn).
•    Experience working with GCP or similar cloud platforms.
•    Hands-on experience with time-series forecasting, regression models, and ensemble methods.
•    Strong SQL experience and comfort with large-scale datasets.
•    Ability to diagnose data issues, perform anomaly analysis, and build automated alerting solutions.

Preferred Qualifications
•    Experience in retail, supply chain, inventory, or demand forecasting systems.
•    Exposure to MLOps practices (CI/CD, model monitoring, retraining pipelines).