Data Scientist - Credit Risk Models

As a Data Scientist - Credit Risk Models, you'll apply advanced statistical and quantitative techniques to develop and enhance models that help us understand portfolio vulnerabilities, assess resilience under adverse scenarios and support better risk decisions. As such, you may regularly expect to:

• Develop and enhance credit risk stress-testing models using advanced statistical and quantitative techniques.
• Apply approaches including predictive modelling, regression, time-series analysis, panel-data methods and macroeconomic modelling.
• Translate economic and portfolio scenarios into measurable credit-risk impacts, including changes in PD, LGD, exposure and expected credit loss.
• Analyse model behaviour, sensitivities, limitations and key risk drivers to understand how portfolios may respond under different conditions.
• Work with large and complex datasets, including incomplete or imperfect data, and determine practical, well-governed approaches to analytical challenges.
• Use R, Python and SQL, alongside relevant data and cloud platforms, to prepare data, perform analysis and develop models.
• Translate technically complex modelling outcomes into clear insights that can be understood by both technical and non-technical stakeholders.
• Document methodologies, assumptions, limitations and modelling decisions clearly, supporting independent review and validation.
• Partner across the modelling lifecycle with model users, independent model validation and business risk teams.
• Explore thoughtful uses of AI and emerging tools to improve analysis, learning, documentation and productivity, while maintaining appropriate human judgement and accountability.

You'll be someone who genuinely enjoys quantitative problem-solving. You're comfortable getting into the detail of data and statistical methodology, but equally interested in understanding what the results mean and why they matter. To this role, you'll bring:

• A tertiary qualification in a quantitative discipline such as Mathematics, Statistics, Econometrics, Engineering or Data Science with a strong academic performance in your quants heavy modules.
• Experience in quantitative modelling, statistical modelling, data science, econometrics, actuarial science, credit risk analytics or another highly quantitative discipline.
• Strong foundations in statistical and predictive modelling, with exposure to techniques such as regression, time-series analysis, macroeconomic modelling or machine learning.
• Hands-on programming capability using R and/or Python, with experience using SQL to analyse complex datasets.
• The ability to work through ambiguous analytical problems, interrogate imperfect data and reach well-reasoned conclusions.
• Strong written and verbal communication skills, particularly the ability to explain methodology, assumptions, limitations and the practical implications of your analysis.
• Curiosity, sound judgement and a willingness to learn new modelling approaches and technologies.
• Experience with credit risk modelling, PD/LGD/EAD, IRB, IFRS 9 or stress testing would be highly regarded, though not an essential prerequisite.

What's In It for You

This is an opportunity to deepen your technical capability in a sophisticated, highly regulated modelling environment where your work has a clear connection to real risk and business decisions. You'll gain exposure to forward-looking credit risk modelling, complex portfolio and economic scenarios, and experienced practitioners across modelling, validation, risk and the broader business. The role provides visibility beyond the mechanics of building models into how modelling insights inform portfolio management, planning and risk decision-making.

You'll also be part of CommBank's broader Data Science community, which connects Data Scientists across the Group through shared capability frameworks, learning pathways, tooling and AI-enabled ways of working.