You will operate in a highly collaborative environment where analytics is deeply embedded into decision-making and where models are expected to be robust, scalable, and production-ready. What You’ll Be Doing: Independently validate machine learning models across: Credit risk modelling Customer propensity and behavioural modelling Fraud detection and AML (financial crime) models Apply advanced machine learning techniques, including: Supervised learning (XGBoost, CatBoost, Random Forest, Neural Networks) Unsupervised learning (clustering, anomaly detection, isolation forests) Manage the full model lifecycle: Feature engineering and data preparation Model training, evaluation, and selection Deployment support and ongoing performance monitoring Build, review, and challenge models in Python-based environments using large, complex datasets Lead technical discussions and provide mentorship to junior analysts and data scientists Collaborate closely with Risk, Technology, and Business stakeholders to ensure alignment Ensure models meet governance, performance, and scalability standards across the organisation What We’re Looking For: 6–8+ years’ experience in quantitative analytics, data science, or machine learning Strong end-to-end model development experience using Python Advanced SQL skills and experience working with large datasets Deep experience in techniques such as: Gradient boosting (XGBoost, CatBoost) Neural networks Clustering and anomaly detection Experience in credit risk, behavioural analytics, or financial crime modelling Exposure to model validation, peer review, or model risk frameworks Strong ability to balance technical depth with stakeholder engagement Qualifications: Honours or Master’s degree in Mathematics, Statistics, Computer Science, Actuarial Science, or a related quantitative field Preferred Experience: Experience leading or mentoring data science / ML teams Exposure to regulated financial environments Cloud-based model deployment experience Credit scoring, IFRS analytics, or scorecard modelling exposure Familiarity with model governance and validation standards Why Join? Work on high-impact models used across a major banking environment Exposure to a wide variety of modelling applications (not siloed work) Strong mentorship from experienced quantitative and risk leaders A culture built on simplicity, ownership, and transparency Excellent long-term career growth and learning opportunities Requirements: Clear criminal and credit record #J-18808-Ljbffr