Data Science

About the role

We are seeking a Data Scientist to join our hybrid team in Bengaluru. You will focus on building robust predictive models and extracting insights from complex datasets. This role requires a strong foundation in statistical analysis and machine learning, with a specific emphasis on end-to-end model development from data exploration to deployment monitoring. You will work closely with engineering and product teams to solve business problems using data-driven approaches.

Responsibilities

• Perform Exploratory Data Analysis (EDA) to understand data distributions, identify anomalies, and define key features for modeling.

• Design and implement feature engineering pipelines to transform raw data into high-quality inputs for machine learning algorithms.

• Build and train classification models using Logistic Regression, Decision Trees, Random Forest, and XGBoost.

• Write efficient Python code using Pandas, NumPy, and Scikit-learn to process large and messy datasets.

• Develop SQL queries to extract and aggregate data from relational databases for analysis and model training.

• Evaluate model performance using statistical metrics and validate results against business objectives.

• Implement basic model monitoring scripts to track data drift and model degradation in production environments.

Required skills

• Proficiency in Python with extensive experience in Pandas, NumPy, and Scikit-learn.

• Strong command of SQL for data extraction, manipulation, and analysis.

• Solid understanding of machine learning algorithms, specifically Logistic Regression, Decision Trees, Random Forest, and XGBoost.

• Experience with statistical hypothesis testing and model evaluation metrics (AUC, F1, Precision, Recall).

• Ability to handle large, unstructured, or messy datasets with minimal data cleaning overhead.

• Basic knowledge of MLOps concepts and model monitoring practices.

Nice to have

• Experience with cloud platforms like AWS or GCP for data storage and compute.

• Familiarity with version control systems like Git for code management.

• Exposure to containerization tools like Docker for model deployment.

• Knowledge of A/B testing frameworks for experiment design.

What success looks like

• You deliver accurate predictive models that improve key business KPIs by measurable percentages.

• Your feature engineering pipelines reduce model training time and improve data quality.

• You establish reliable monitoring systems that detect model drift before it impacts business outcomes.

• You collaborate effectively with engineers to integrate models into production systems with minimal friction.