This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
The purpose of this role is to build high-quality risk models that estimate risk costs (frequency, severity and pure premium) as accurately as possible using state-of-the-art techniques. Ensure rigorous data cleansing and preparation, validate model outputs against financial results and portfolio performance, produce comprehensive documentation, and actively incorporate feedback from key stakeholders (Portfolio, Reserving and Underwriting) to refine and maintain models.
Job Responsibility:
Own the end-to-end modelling lifecycle: problem framing, data build, feature engineering, model development, validation, documentation
Build and maintain risk and price models using GLMs and machine learning
Translate models into implementable rating structures
Strong governance: change control, champion–challenger/shadow runs, rollback plans, and clear approvals and audit trails
Requirements:
Strong general insurance pricing toolkit: GLMs (Poisson/NB/Tweedie), GAMs, credibility/hierarchical methods
experience with tree-based ML (GBM/XGBoost/CatBoost) and regularisation
Proficient in R and Python, with strong SQL
comfortable in Git-based workflows and “in the engine room” with proprietary rating systems
Hands-on experience taking models from concept to live in rating engines
robust validation, change control and post-live monitoring
Familiarity with peril/exposure enrichment relevant to home insurance (e.g. flood and subsidence datasets) and geospatial modelling considerations
Awareness of reserving concepts, claims inflation and their interaction with technical pricing
Knowledge of model risk management, documentation standards and governance under UK regulation (Consumer Duty, Fair Value Assessments, GIPP)