This is a hands‑on technical role for an experienced machine learning professional who enjoys working end‑to‑end on complex models in a regulated environment and providing some strong analytical challenges to production models.You will play a key role within a specialist quantitative function responsible for the independent validation and oversight of machine learning and data science models used across the organisation. These models support critical decision‑making in areas such as credit risk, fraud, AML, and customer behaviour. The role combines deep technical modelling work with leadership responsibilities, including mentoring Junior Analysts and partnering closely with Risk, Technology, and Business teams to ensure that models are robust, scalable, and production‑ready.Key Responsibilities: Lead the independent validation of machine learning models, including:Credit risk models Propensity and behavioural models Financial crime models (fraud and AML) Apply advanced machine learning techniques, such as:Supervised learning (Random Forest, XGBoost, CatBoost, and Neural Networks) Unsupervised learning (clustering, isolation forests, and anomaly detection) Manage model risk across the full model lifecycle, including:Feature engineering and data preparation Model training, evaluation, and selection Deployment readiness and ongoing monitoring Build, assess, and review models in Python-based environments Provide technical leadership and mentorship to Analysts and Junior Data Scientists Partner with Risk, Technology, and Business stakeholders on model oversight Ensure adherence to governance, performance, and scalability standards Job Experience and Skills Required: Education: Honours or Masters degree in Mathematics, Statistics, Computer Science, Actuarial Science, or a related quantitative field Experience: 68+ years experience in data science, machine learning, or quantitative analytics Hands-on leadership experience delivering models end-to-end Experience in credit risk, propensity modelling, and/or financial crime Exposure to independent model validation or strong peer review Experience in regulated environments Skills: Machine learning techniques: XGBoost, CatBoost, Random Forest, and Neural Networks Clustering and anomaly detection Advanced Python and solid SQL skills Strong understanding of the full model lifecycle Ability to work across technical and business stakeholders For more exciting Actuarial and Analytics vacancies, please visit: