We are looking for a Principal Data Scientist to lead the development of credit and fraud risk models and to raise the standard of data science across our risk function. This is a hands-on role. You will build, validate and deploy models yourself, while also setting technical standards, shaping modelling strategy and presenting findings and recommendations to senior stakeholders.

Design, build and implement statistical and machine learning models for credit risk (PD, LGD, EAD, application and behavioural scorecards, early warning) and fraud detection (transaction, application and account-takeover fraud). Extend modelling work into customer and operational risk, identifying new use cases where data science can reduce loss and improve outcomes. Own the end-to-end model lifecycle: problem framing, data exploration, feature engineering, development, validation, deployment, monitoring and recalibration. Set and champion data science standards, including modelling methodology, code quality, documentation, reproducibility and model governance. Partner with Model Risk Management, Risk, Compliance and Technology teams to ensure models meet regulatory and internal governance requirements (for example IFRS 9, Basel, SS1/23 model risk principles or local equivalents). Communicate complex analytical findings clearly to senior stakeholders and executive committees, translating technical results into business impact and decisions. Provide technical guidance, peer review and mentoring to other data scientists and analysts, without formal line-management responsibility. Evaluate new techniques, tools and data sources, and recommend where they add value over established approaches. Work with engineering and platform teams to productionise models on Databricks and Azure, in line with MLOps best practice.

10+ years of experience in applied data science, statistical modelling or quantitative analytics. PhD or MSc in a quantitative discipline such as Statistics, Econometrics, Mathematics, Data Science, Physics or a related field. Strong grounding in statistics and econometrics, including regression and GLMs, survival analysis, time series, causal inference and model validation techniques. Proven track record of building and deploying predictive models in a credit, fraud or comparable risk setting. Advanced proficiency in Python and R, and strong SQL skills for working with large datasets. Hands-on experience with Databricks (including Spark and MLflow) and Azure Data Services (for example Azure Data Factory, Synapse, Azure ML, Data Lake Storage). Experience with machine learning techniques such as gradient boosting, ensemble methods and anomaly detection, with an understanding of when simpler, more interpretable models are preferable. Excellent communication and stakeholder management skills, with experience presenting to senior and non-technical audiences. Demonstrated ability to set standards and influence practice across a team or function without direct authority.