Applied Data Scientist

Role Overview

We are seeking an Applied Data Scientist with strong expertise in Credit Risk Modeling to build scalable AI/ML solutions for lending and risk decisioning. The ideal candidate should have hands-on experience in BFSI/Lending, statistical modeling, machine learning, and credit risk frameworks.

Key Responsibilities

• Build and deploy Application Scorecards, Behavioral Models, and Portfolio Risk Models.
• Develop PD, LGD, and ECL models aligned with BASEL II and IFRS9.
• Apply Logistic Regression, GLM, XGBoost, and other ML techniques for credit risk.
• Perform feature engineering, EDA, and large-scale data processing using SQL, Spark/PySpark.
• Use PCA and K-Means for customer segmentation and risk analysis.
• Collaborate with Product, Engineering, and Business teams to deliver production-ready ML solutions.
• Improve model performance, explainability, and governance.
• Mentor junior team members and contribute to ML best practices.

Required Experience

• 4–7 years in Applied Data Science, Risk Analytics, or Credit Risk Modeling within BFSI/Lending.
• Strong experience with Credit Bureau data, scorecards, behavioral models, and regulatory risk frameworks.
• Hands-on knowledge of Machine Learning, Statistical Modeling, and Deep Learning.
• Exposure to Generative AI, RAG, Agentic AI, Prompt Engineering, or LLMs is a plus.

Technical Skills

• Programming: Python, SQL
• Data Processing: Pandas, Spark/PySpark
• ML Libraries: Scikit-learn, XGBoost, TensorFlow, PyTorch
• Modeling: Logistic Regression, GLM, XGBoost, PCA, K-Means
• Domain: Credit Risk, PD, LGD, ECL, BASEL II, IFRS9, Credit Bureau Data