Machine Learning Engineer

Client of Kalamntina

Responsibilities:

• Proven hands-on experience developing, deploying, and maintaining machine learning models for credit scoring or credit risk, with direct impact on credit decisioning systems.
• Strong understanding of statistical modeling and supervised learning techniques, including logistic regression, decision trees, random forests, gradient boosting (XGBoost, LightGBM), and ensemble methods.
• Ability to select, tune, and optimize models for highly imbalanced credit and risk datasets.
• Extensive experience with feature engineering using financial, transactional, and alternative data sources such as transaction histories, payment behavior, mobile money data, telco data, or other non-traditional indicators.
• Expert proficiency in Python, with strong hands-on experience using scikit-learn, XGBoost, LightGBM, and deep learning frameworks such as TensorFlow or PyTorch when required.
• Strong knowledge of model validation, monitoring, and lifecycle management, including drift detection and ongoing performance evaluation.
• Familiarity with credit risk performance metrics, including Gini coefficient, KS statistic, AUC-ROC, precision-recall, calibration, and Population Stability Index (PSI).