Data Scientist

About the role

We're looking for a Data Scientist to join our team and help turn one of the richest logistics datasets in the country into models and insights that directly improve how millions of shipments are delivered. You'll work on real problems, predicting delivery dates, detecting and resolving delivery failures, estimating live ETAs, building recommendation and anomaly-detection systems, and surfacing insights that drive product and business decisions.

What you'll do

• Build, train, and evaluate machine learning and deep learning models for real logistics problems, delivery date prediction (EDD), delivery-failure (NDR) resolution
• Explore large, messy, real-world datasets end-to-end: variable identification, data cleaning, feature engineering, dimensionality reduction
• Build and maintain data pipelines (batch & streaming) on Databricks using Spark, PySpark, and Delta Lake
• Write clean, well-documented code in Python (pandas, NumPy, scikit-learn, Matplotlib) for analysis, modeling, and production
• Deploy models to production and own their lifecycle, monitoring, validation, drift detection, and continuous improvement

What you need

• 2–4 yrs of experience
• Machine learning
• Python
• SQL
• Pandas
• Scikit-learn
• LLMs
• B.Tech or B.E.

Good to have

• Computer vision
• Spark
• AWS
• Deep learning
• Data modelling
• Databricks