Data Scientist

Overview

In this role you will help build credit risk and pricing models for a fintech platform serving local businesses. You will work across the model lifecycle, from exploration to deployment, collaborating with cross-functional teams to influence credit decisions and portfolio performance. You will learn from senior data scientists and contribute to live products used by Members. This is a fast-growing environment where rigorous, business-relevant data science has a direct impact.

Pay / Benefits

• flexible working hours
• WellHub health support
• extended maternity/paternity leave
• Cycle-to-Work Scheme
• Health and Life Insurance
• Pension Scheme

Responsibilities

• Build and test components of credit risk and pricing models under guidance
• Explore internal and external data sources, clean datasets, and engineer features
• Analyze merchant behaviour, repayment and product performance to answer business questions
• Monitor model performance, flag drift, and support investigations
• Assist deployment of models onto the ML Platform and integration with credit decisioning
• Document work clearly for review and reuse
• Collaborate with Product, Engineering, Data Engineering and Credit Strategy, seeking feedback from senior data scientists

Key requirements

• 0–2 years’ experience in data science, quantitative analysis or related field
• Degree in a quantitative field such as Mathematics, Statistics, Physics, Engineering, Computer Science or related discipline
• Solid grounding in statistics and core machine learning techniques
• Working knowledge of Python and SQL with experience handling real-world datasets
• Ability to explain analytical work to technical and non-technical stakeholders
• Curious, pragmatic and commercially minded with curiosity about how models drive business outcomes
• Willingness to learn and grow in a collaborative team
• Exposure to credit risk modelling or financial services is a plus

• clear communication
• collaboration
• curiosity
• statistical modelling
• machine learning techniques
• feature engineering

…