Data scientist

Sourcebae; Mumbai; On-site; INR 2,000,000 - 3,600,000; Full time

Job summary

Sourcebae is seeking a Senior Data Scientist to lead machine learning initiatives, develop predictive and prescriptive analytics, and deliver scalable analytical solutions. You will translate business problems into data-driven models, work with cross-functional teams, and ensure robust model deployment and monitoring.

Ideal candidates have 5+ years of data science experience, strong SQL/BigQuery capabilities, and hands-on expertise with Python-based ML libraries.

Qualifications

• 5+ years of experience in data science.
• Experience building ML models for customer analytics and marketing optimization.
• Strong SQL and BigQuery skills; able to optimize large-scale data processing.

Responsibilities

• Design, develop, deploy, and monitor machine learning models.
• Build predictive and prescriptive analytics for customer acquisition, churn, CLV, and cross-sell.
• Perform EDA on large datasets and deliver actionable insights to stakeholders.

Skills

Python

SQL

PySpark

Jupyter Notebook

Tools

Scikit-learn

XGBoost

LightGBM

CatBoost

Statsmodels

Mlflow

Neural Networks

Google BigQuery

PostgreSQL

MySQL

SQL Server

Job description

Role Overview: We are seeking a highly analytical and business-oriented Senior Data Scientist to join our Data Science team. The ideal candidate will possess strong expertise in Machine Learning, SQL, BigQuery, advanced analytics, and large-scale data processing. This role will be responsible for developing Machine Learning models, generating customer insights, deliver predictive, descriptive and prescriptive analysis and building scalable analytical solutions that drive business growth and customer engagement. The candidate should be comfortable working with large datasets, collaborating with cross-functional stakeholders, and translating business problems into data-driven solutions.

Key Responsibilities:

1. Machine Learning & Advanced Analytics

• Design, develop, deploy, and monitor machine learning models.
• Build predictive models for customer acquisition, propensity scoring, response modeling, cross-sell/up-sell, churn prediction, customer lifetime value (CLV), and risk-adjusted marketing strategies.
• Apply statistical techniques and machine learning algorithms to solve complex business problems.
• Conduct model validation, performance monitoring, and periodic recalibration.
• Develop customer segmentation frameworks and targeting strategies.
• Design and execute A/B testing and experimentation frameworks.

2. Data Analysis & Business Insights

• Perform exploratory data analysis (EDA) on large structured and unstructured datasets.
• Build automated reporting and analytical frameworks to support business decision-making.
• Identify trends, opportunities, and risks through advanced data analysis.
• Present insights and recommendations to senior stakeholders in a clear and concise manner.

3. Data Engineering & Cloud Analytics

• Optimize SQL queries and data processing for large-scale datasets.
• Collaborate with data engineering teams to ensure high-quality and reliable data assets.
• Ensure data governance, quality, and consistency across analytical solutions.

4. Model Deployment & MLOps

• Support end-to-end model lifecycle management from development to production deployment.
• Work with engineering teams to operationalize machine learning solutions.
• Implement model monitoring, drift detection, and performance tracking mechanisms.
• Contribute to best practices in MLOps and model governance.

Preferred Tech Stack:

• Programming & Data Analysis – Python, SQL, PySpark, Jupyter Notebook
• Machine Learning & Statistical Modelling - Scikit-learn, XGBoost, LightGBM, CatBoost, Statsmodels, Regression, Clustering, Mlflow, Neural Networks
• Customer Analytics - Customer Segmentation, Propensity Modelling, Cross-Sell Models, Churn Prediction, Customer Lifetime Value (CLV), Campaign Measurement, Attribution Modelling, A/B Testing, Uplift Modelling, Recommendation Systems
• Data Warehousing & Databases - Google BigQuery (Mandatory), PostgreSQL, MySQL, SQL Server
• Cloud Platforms – BigQuery, Cloud Run, Vertex AI

Years of Experience:

Overall Experience: 5+ years of experience

Preference: BFSI Experience will be preferred but not mandatory