Credit Risk Modeling, Machine Learning & Analytics

| Credit Risk Modeling, Machine Learning & Analytics Roles Openings Across: Multiple Credit Risk Modeling and Analytics Roles Location: Gurugram, India Job ID: CR-ML-GUR Experience: 3-7 Years of relevant experience Compensation: 25-36 LPA : At Risk Inn, we specialize in connecting leading banks, investment institutions, consulting firms, family offices, and financial services clients with high-quality talent across risk management, quantitative finance, financial markets, investment research, and analytics. Through our curated professional communities and practitioner-driven ecosystem, we bring relevant career opportunities to finance, risk, data, and analytics professionals globally. Our goal is to bridge the gap between skilled professionals and roles that meaningfully contribute to both individual career growth and organizational impact. We are supporting the Risk & Compliance Analytics practice of a leading global data, AI, analytics, and consulting firm in hiring experienced professionals for multiple credit risk modeling opportunities. These roles are suitable for professionals with strong experience in statistical and machine-learning modeling across credit risk, credit strategy, behavioral scoring, fraud analytics, PD, LGD, IFRS 9, and other banking-focused use cases. Strong proficiency in Python, SQL, NLP, XGBoost, model monitoring, explainability, and stakeholder management will be important for these opportunities. Think youre the right fit Keep reading! : , & Develop, validate, and maintain statistical and machine-learning models for credit risk assessment across banking and consumer-lending portfolios Build end-to-end models for underwriting, acquisition, behavioral scoring, account management, collections, recovery, fraud detection, PD, LGD, and IFRS 9 use cases Extract, clean, and analyze large structured and unstructured datasets using Python and SQL to support model development and performance monitoring Perform exploratory data analysis, feature engineering, variable selection, missing-value treatment, class-imbalance handling, model selection, and hyperparameter tuning Develop and compare models using logistic regression, gradient boosting, XGBoost, random forest, NLP, and other statistical or machine-learning techniques Evaluate model performance through discrimination, calibration, back-testing, stability analysis, benchmarking, and relevant classification metrics Apply model-explainability and interpretability techniques to identify key risk drivers and support transparent credit decisions Monitor model performance, data drift, population stability, and emerging deterioration, and recommend recalibration, redevelopment, or challenger models where required Translate credit-risk and business requirements into analytical solutions while collaborating with client stakeholders across Risk, Underwriting, Collections, Product, Finance, Technology, and Model Validation Prepare model-development documentation, methodology notes, validation responses, analytical presentations, and decision-ready recommendations in line with governance and client requirements Strong hands-on experience in end-to-end credit risk model development within banking, financial services, fintech, analytics, or consulting Advanced proficiency in Python and SQL for data extraction, data preparation, statistical analysis, model development, and monitoring Strong practical knowledge of machine learning, XGBoost, Natural Language Processing, logistic regression, gradient boosting, random forest, and classification techniques Experience with Python libraries such as Pandas, NumPy, scikit-learn, XGBoost, and relevant NLP libraries or frameworks Experience developing acquisition, underwriting, behavioral, collections, recovery, fraud, PD, LGD, or IFRS 9 models Strong understanding of retail credit products and lending lifecycle stages, including application assessment, account management, delinquency, collections, recovery, and default Knowledge of feature engineering, variable selection, hyperparameter tuning, model calibration, back-testing, benchmarking, and champion-challenger analysis Understanding of model-performance measures such as ROC-AUC, Gini, KS, precision, recall, F1 score, confusion matrices, calibration measures, and population-stability indicators Knowledge of model explainability, feature importance, fairness assessment, model limitations, and governance expectations for machine-learning models A | Credit Risk Modeling, Machine Learning & Analytics Roles Openings Across: Multiple Credit Risk Modeling and Analytics Roles Location: Gurugram, India Job ID: CR-ML-GUR