Requirements

Expected technologies

Python

SQL

Our requirements

• 3+ years of experience as an ML Engineer / Data Scientist in a financial or regulated environment.
• Strong understanding of traditional risk modeling techniques: logistic regression, scorecard models, survival analysis, Markov chains.
• Hands-on experience with ML algorithms such as XGBoost, LightGBM, Random Forest, or deep tabular models.
• Proficiency in Python (e.g., scikit-learn, xgboost, lifelines, SHAP, pandas) and SQL.
• Familiarity with regulatory requirements in credit risk (e.g., ECL, IFRS 9, Basel III).
• Strong communication skills and ability to explain model logic to non-technical stakeholders (e.g., risk, compliance, audit).

Your responsibilities

• Develop predictive models for credit scoring, loan deterioration, and time-to-default (e.g., logistic regression, scorecards, survival models, Markov chains).
• Perform data exploration and feature engineering using behavioral and transactional credit data (payments, delinquencies, account activity).
• Ensure model performance, robustness, and interpretability (e.g., PSI, SHAP, monitoring).
• Collaborate with Data Engineering teams to deploy models into production pipelines (batch or real-time scoring).
• Contribute to model audit, validation, and documentation processes.