Lead Data Scientist (ECL Modelling)

Get To Know Our Company

GX Bank Berhad - the Grab-led Digital Bank - is the FIRST digital bank in Malaysia, approved by BNM to commence operations. We aim to leverage technology and innovation to serve the financial needs of the unserved and underserved individuals, and micro and small medium enterprises.

We are driven by our shared purpose and passion to bring positive transformation to the banking industry, starting with solutions that address the financial struggles of Malaysians and businesses.

Get To Know The Role

We are looking for an experienced credit risk modeller to lead the development and enhancement of Expected Credit Loss (ECL) models for our Retail and MSME portfolios.

The role is primarily focused on hands-on MFRS 9 ECL modelling—including Probability of Default (PD), Loss Given Default (LGD) and Exposure at Default (EAD)—with additional responsibility for credit risk scorecards, portfolio analytics and model implementation. You will use Python and SQL to develop transparent, scalable and well-governed models suitable for a digital banking environment.

Key Responsibilities

• Lead the end-to-end development, implementation and enhancement of MFRS 9 ECL models across Retail and MSME portfolios.
• Develop 12-month and lifetime PD models, including term structures, point-in-time calibration and the incorporation of forward-looking macroeconomic information.
• Develop LGD models covering recovery patterns, cure behaviour, workout periods, collateral, costs and discounting.
• Develop EAD and credit conversion factor models for term loans and revolving credit facilities.
• Design and enhance ECL methodologies covering portfolio segmentation, default definitions, significant increase in credit risk, staging and multiple economic scenarios.
• Develop application, behavioural and collection scorecards using traditional statistical methods and, where appropriate, machine-learning techniques.
• Perform model calibration, back-testing, benchmarking, sensitivity analysis, stress testing and ongoing performance monitoring.
• Translate modelling methodologies into robust, modular and reproducible Python implementations.
• Build reliable analytical datasets and model pipelines using Python and SQL, working closely with Data Engineering and Technology teams.
• Produce comprehensive model documentation and support independent validation, audit, governance committees and regulatory reviews.
• Partner with Credit Risk, Finance and Business teams to explain ECL movements, portfolio trends and the financial impact of model changes.
• Contribute to the Bank’s broader credit risk modelling, portfolio optimisation and capital-management frameworks.
• Provide technical guidance and mentorship to other modellers and analysts.
  
  

The Must Haves

• At least eight years of relevant experience in credit risk modelling, quantitative risk, data science or advanced credit analytics within banking, financial services or consulting.
• Strong hands-on experience developing MFRS 9 or IFRS 9 ECL models, with demonstrated expertise in PD and practical experience across LGD and EAD modelling.
• Deep understanding of ECL concepts, including 12-month and lifetime expected losses, staging, significant increase in credit risk and forward-looking macroeconomic scenarios.
• Experience developing and monitoring credit risk scorecards for Retail, MSME or similar lending portfolios.
• Advanced proficiency in Python for statistical modelling and data analysis, using libraries such as pandas, NumPy, scikit-learn and statsmodels.
• Strong SQL skills and experience working with large, complex and longitudinal credit datasets.
• Knowledge of relevant modelling techniques, including logistic regression, survival analysis, transition matrices, time-series or macroeconomic modelling, and recovery analysis.
• Experience managing the complete model lifecycle, including data preparation, methodology development, implementation, monitoring, documentation and remediation.
• Sound understanding of model risk governance, validation standards and regulatory expectations.
• Ability to communicate complex methodologies and modelling results clearly to senior, technical and non-technical stakeholders.
• Bachelor’s or Master’s degree in Statistics, Mathematics, Econometrics, Data Science, Computer Science, Engineering, Finance or another quantitative discipline.
  
  

Good to Have

• Experience with Basel credit risk models, IRB models, stress testing or capital modelling.
• Experience deploying models into production and working with Git, automated testing, CI/CD or model-monitoring frameworks.
• Familiarity with AWS services and cloud-based data or modelling platforms.
• Experience in digital banking, fintech or portfolios with limited historical data.
• Professional qualifications such as FRM, CFA, Chartered Banker or an equivalent risk qualification.