Lead Credit Risk Data Scientist – Real-Time Scoring

Klarna; Greater London; On-site; GBP 110,000 - 150,000; Full time

Job summary

Klarna is seeking a Lead Data Scientist to shape the next generation of consumer-level credit scoring and portfolio valuation models. You will design and maintain real-time PD models and calibration frameworks for underwriting and return optimization.

Collaborate with cross-functional teams, translate insights into policy, and mentor junior staff. Strong Python/SQL, XGBoost, scikit-learn, and MLFlow experience required; familiarity with SHAP/LIME/PDP for explainability is preferred.

Qualifications

• 5+ years' experience in credit risk modeling for consumer lending, credit cards, or BNPL.
• Proficient in PD model development and validation with calibration techniques.
• Advanced Python and SQL skills; familiarity with XGBoost, scikit-learn, pandas, MLFlow.
• Experience with explainability frameworks such as SHAP, LIME, PDP.
• Ability to communicate complex concepts clearly and influence cross-functional decisions.
• Familiarity with real-time modeling and current ML/credit analytics trends.

Responsibilities

• Shape next-generation consumer-level credit scoring and portfolio valuation models.
• Design and maintain real-time PD models and calibration frameworks.
• Integrate models into underwriting and economic return frameworks.
• Ensure regulatory compliance and fairness standards; explore new methodologies.
• Collaborate with cross-functional teams and mentor junior members.

Skills

Credit risk modeling

PD modeling

Calibration

Python

SQL

XGBoost

scikit-learn

Pandas

MLFlow

Explainability

Communication

Cross-functional

Real-time modeling

Tools

MLFlow

SHAP

LIME

PDP

Job description

Klarna is seeking a Lead Data Scientist to shape the next generation of consumer-level credit scoring and portfolio valuation models. You will design and maintain real-time PD models and calibration frameworks for underwriting and return optimization.

Collaborate with cross-functional teams, translate insights into policy, and mentor junior staff. Strong Python/SQL, XGBoost, scikit-learn, and MLFlow experience required; familiarity with SHAP/LIME/PDP for explainability is preferred.