We are looking for a Data Scientist with hands-on experience in building and evaluating Machine Learning models who can take a problem from problem definition and data preparation through model development and deployment into production.

Prior experience in Credit Risk is not required. However, an interest in and ability to learn financial and credit risk concepts, and translate business problems into modeling problems, is important for this role.

Responsibilities:

• Analyze transactional and behavioral data and perform feature engineering to identify meaningful variables for modeling
• Develop, evaluate, and optimize Machine Learning models
• Select and compare algorithms such as Logistic Regression, XGBoost, LightGBM, CatBoost, and, when appropriate, Deep Learning models based on the problem
• Design appropriate train/validation strategies and evaluate models using metrics such as AUC/ROC, Precision-Recall, KS, Calibration, and Stability
• Develop challenger models and analyze the strengths and weaknesses of different modeling approaches
• Analyze feature importance and model explainability methods
• Perform backtesting, cohort analysis, and, when needed, simulation to assess the impact of models on portfolio performance
• Collaborate with Engineering and MLOps teams to deploy models into production
• Monitor model performance and data quality, and investigate drift and changes in model performance
• Document models, assumptions, and results, and communicate them effectively to technical and business stakeholders

Requirements:

• 2 years of hands-on experience in Data Science / Machine Learning
• Experience developing at least one Machine Learning model that has been deployed to production or used in a real business decision
• Hands-on experience with Machine Learning algorithms, particularly tree-based models and Logistic Regression
• Strong foundation in statistics and a good understanding of model evaluation, sampling, hypothesis testing, and calibration
• Practical understanding of concepts such as data leakage, class imbalance, overfitting, and feature engineering
• Experience with Git and familiarity with tools such as MLflow and Airflow
• Ability to analyze model results and clearly communicate technical concepts and trade-offs to non-technical stakeholders

Nice to have:

• Experience in Credit Risk, FinTech, Banking, or Consumer Lending
• Familiarity with concepts such as PD, Credit Scoring, NPL, Vintage Analysis, PSI, and Scorecards
• Experience with model monitoring and production ML
• Familiarity with causal inference and causal impact analysis for evaluating the effects of policy, product, or behavioral changes
• Experience with forecasting, simulation, or experimentation
• Familiarity with explainable ML techniques
• Familiarity with model serving using tools such as FastAPI, Docker, or similar technologies
• Academic background in Finance, Economics, Banking, Financial Management, Financial Engineering, or related fields