Data Science

Kotak Mahindra Bank; Bengaluru; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Kotak Mahindra Bank in Bengaluru is seeking a Data Scientist to build predictive models, ML solutions, and optimization pipelines for credit risk, fraud analytics, and customer journeys. You will work with cross-functional teams to translate business needs into data-driven insights and deploy end-to-end solutions.

The role requires 2–6 years of experience and a strong Python/SQL/PySpark stack, plus familiarity with BFSI analytics, model governance, and MLOps practices.

Qualifications

• Bachelor's or Master's in Statistics, Economics, Mathematics, CS, Data Science or related field.
• Proficiency in Python, SQL, PySpark and ML libraries.
• Experience with BFSI analytics and risk/fraud domains is preferred.

Responsibilities

• Model development: build and deploy ML models for credit risk, fraud, and customer lifecycles.
• Optimize pipelines with robust version control and lifecycle practices.
• Perform EDA, feature engineering, and collaborate with cross-functional teams for deployment.
• Support MLOps monitoring and model explainability (SHAP/LIME).

Skills

Python

SQL

PySpark

Education

Bachelor's or Master's in a quantitative field

Tools

scikit-learn

TensorFlow

PyTorch

Airflow

MLflow

Job description

College - Tier 1 mandatory

Preferred candidate profile

A Data Scientist job description at Kotak Mahindra Bank typically focuses on building predictive models, machine learning solutions, and optimization pipelines for credit risk, fraud analytics, and customer experience journeys. [1, 2]Role Overview

• Department: Analytics / Digital Banking / CVM CoE
• Locations: Bengaluru
• Experience Range: Typically 2 to 6 years

Key Responsibilities

• Model Development: Build and deploy machine learning algorithms, propensity models, classification, regression, clustering, and GenAI/LLM solutions across customer lifecycles.
• Optimized Coding: Write efficient, scalable code for model pipelines using robust version control and lifecycle configuration practices.
• Data Exploration & Feature Engineering: Conduct exploratory data analysis (EDA), translate business needs into data-driven insights, and manage feature repositories.
• Collaboration & Deployment: Partner with cross-functional product, risk, engineering, and compliance teams to ensure end-to-end implementation, MLOps monitoring, and explainability (SHAP/LIME).

Key Requirements & Skills

• Education: Bachelor's or Master's degree in Statistics, Economics, Mathematics, Computer Science, Data Science, or a related quantitative field.
• Technical Stack: Strong proficiency in Python, SQL, and PySpark.

• Frameworks: Experience with machine learning libraries such as scikit-learn, TensorFlow, PyTorch, and workflow tools like Airflow or MLflow.
• Domain Knowledge: Familiarity with BFSI (Banking, Financial Services, and Insurance) analytics, bureau/transactional data, and credit/fraud risk management is heavily preferred