Senior Data Scientist – Credit Risk (Banking)

About the role

We are seeking a hands‑on Senior Data Scientist with banking or financial services experience, focusing on credit risk and lending. The role involves developing, validating, deploying and monitoring machine‑learning models for loan underwriting, default prediction and customer analytics.

Key responsibilities

• Translate business requirements into modelling objectives, define targets and success criteria.
• Develop credit scoring, loan underwriting and probability‑of‑default models using algorithms such as Random Forest, XGBoost, LightGBM and CatBoost.
• Perform data preparation, feature engineering, feature selection and address data leakage, over‑/under‑fitting.
• Conduct hyper‑parameter tuning, cross‑validation and out‑of‑time testing, and select classification thresholds aligned with business priorities.
• Explain model behaviour and individual predictions using SHAP and present results to technical and business stakeholders.
• Collaborate with engineering teams to deploy models, monitor performance, stability and data drift.

Required profile

• Proven experience delivering end‑to‑end machine‑learning projects in banking or financial services, especially credit risk or lending.
• Strong proficiency in Python and SQL for data preparation, analysis and modelling.
• Deep understanding of classification algorithms, bias‑variance trade‑off and evaluation metrics such as ROC AUC, KS, precision, recall, F1 and confusion matrices.
• Ability to communicate technical concepts clearly and link model performance to business KPIs.

Required skills

• Python
• SQL
• Random Forest
• XGBoost
• LightGBM
• CatBoost
• SHAP
• Feature engineering, selection, normalization, standardization
• Model validation (cross‑validation, out‑of‑time testing)
• Understanding of data leakage, overfitting, underfitting