Lead Data Scientist

Overview

As Lead Data Scientist at Cotality, you will steer the technical direction of our predictive modelling efforts and mentor a team of data scientists. You will design and deploy advanced models that power core data products used by major financial institutions, and help shape a scalable data platform. You’ll translate business needs from senior stakeholders into effective analytical solutions, while championing model quality and maintainable production pipelines. This is a high-impact role at a mission-driven fintech-adjacent proptech company, offering hands-on innovation and leadership at scale.

Pay / Benefits

• Generous paid leave
• Up to 16 weeks parental leave
• Private medical cover
• Pension scheme with employer contributions
• Wellbeing and health resources
• Wellbeing allowance

Responsibilities

• Lead design and implementation of advanced predictive models using statistical and ML techniques
• Provide technical leadership and mentorship to data scientists
• Own end-to-end model lifecycle from R&D to production deployment
• Collaborate with senior stakeholders to translate business needs into analytical solutions
• Champion best practices in model development, validation, and maintenance
• Guide technical strategy for core data products and data platform
• Drive innovation and contribute to a culture of excellence
• Partner with Product, Sales, and Leadership to align on insights-based decisions

Key requirements

• 8+ years of experience in developing and deploying high-impact ML models in a commercial environment
• Expert-level knowledge of statistical analysis, predictive modelling, and ensemble techniques (e.g., Gradient Boosted Trees, Random Forests)
• High proficiency in Python (Pandas, Scikit-Learn, XGBoost/LightGBM) and SQL
• Experience with very large, complex datasets; geospatial data experience is advantageous
• Proven ability to mentor and lead technically, guiding complex projects
• Strong communication skills to explain technical concepts to non-technical stakeholders

• leadership
• mentorship
• cross-functional collaboration
• Python for data science (Pandas, Scikit-Learn, XGBoost/LightGBM)
• SQL
• Ensemble methods (Gradient Boosting, Random Forests)

…