Credit Risk Modeller â?? Scorecard Development

Key Responsibilities

• Develop and implement credit scoring models (PD, LGD, IFRS 9) across retail portfolios.
• Apply GLMs, survival analysis, and machine learning algorithms to build predictive, stable, and explainable models.
• Extract and manipulate large structured and unstructured datasets for modelling purposes.
• Conduct feature engineering, model validation, and performance monitoring.
• Collaborate with cross-functional teams across credit, risk, data science, and IT to deploy models into production.
• Lead documentation, governance, and presentation of models to internal risk committees.
• Contribute to research-led initiatives within credit analytics and advanced modelling techniques.

Ideal Candidate Profile

• PhD or MSc in Actuarial Science, Data Science, Applied Statistics, Quantitative Risk, or a related field.
• 5+ years hands-on experience in credit risk modelling in a financial institution or consulting environment.
• Strong proficiency in R, Python, SQL, and tools like SAS, Shiny, or Emblem.
• Expertise in statistical frameworks such as GLMs, Cox regression, Markov models, or survival analysis.
• Experience using alternative data sources (e.g. transactional data, bureau data, behavioural data).
• A research mindset and a strong publication or presentation track record will be a distinct advantage.

Whats in it for You?

• Shape the credit risk modelling roadmap across high-impact portfolios.
• Work on cutting-edge modelling techniques including machine learning, scorecard optimisation, and explainability.
• Join a team known for innovation in IFRS 9, survival modelling, and data science-driven credit strategies.
• Flexible hybrid work model and strong career growth prospects.
• Collaborate in a research-rich, intellectually curious environment.