Data Scientist – Credit Risk & Lending

About the role

The customer seeks a senior Data Scientist with banking experience to lead credit‑risk and lending projects. You will own the full lifecycle of machine‑learning models for loan underwriting, default prediction and customer analytics.

Key responsibilities

• Translate business requirements into modelling objectives, target definitions and success criteria.
• Develop, validate and deploy classification models (Random Forest, XGBoost, LightGBM, CatBoost) for credit scoring and probability of default.
• Perform data preparation, feature engineering, selection and address data leakage, over‑/under‑fitting.
• Conduct hyper‑parameter tuning, cross‑validation and out‑of‑time testing; set 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 on AWS SageMaker and monitor performance, stability and data drift.

Required profile

• 6‑8 years of hands‑on experience in banking or financial services, specifically credit risk, loan underwriting or scoring platforms.
• Proven track record delivering end‑to‑end machine‑learning projects with clear ownership of technical decisions.
• Strong ability to communicate technical concepts and link model performance to business KPIs.

Required skills

• Python
• SQL
• Random Forest, XGBoost, LightGBM, CatBoost
• AWS and Amazon SageMaker
• Optuna (hyper‑parameter optimization)
• SHAP (model explainability)