Data Scientist - Credit Risk (Fintech)

TL;DR

Data Scientist - Credit Risk (Fintech): Developing and enhancing credit risk and pricing models for lending products across multiple geographies with an accent on data exploration, feature development, model deployment, and performance monitoring. Focus on translating business problems into analytical tasks, applying machine learning techniques, and ensuring models deliver real business value.

Location: Onsite in London

Company

hirify.global is a payment and software service provider, headquartered in London, focused on building easy-to-use, integrated tools for small, local businesses across Europe.

What you will do

• Support the translation of credit business problems into analytical and modelling tasks.
• Develop and enhance components of credit risk models and risk-based pricing frameworks.
• Collaborate with Data Engineering for model deployment onto the ML Platform.
• Monitor model performance, investigate changes, and contribute to improvements.
• Explore data sources, engineer features, and assess their predictive value for credit modelling.
• Work with Product, Engineering, Data Engineering, and Credit Strategy to align modelling with business goals.

Requirements

• Hands-on experience in credit risk modelling, ideally in SME lending within fintech or a scale-up.
• Degree in a quantitative field such as Mathematics, Statistics, or Engineering.
• Strong applied quantitative skills, including machine learning techniques.
• Proficiency in Python and SQL with experience working with real-world datasets.
• Ability to explain analytical work clearly to both technical and non-technical stakeholders.
• Curious, pragmatic, and commercially minded, with a desire to understand business outcomes.

Culture & Benefits

• Chance to create impact in a high-energy and connected culture.
• Continuous learning opportunities and a supportive community.
• Comprehensive benefits.
• Commitment to creating an inclusive environment where everyone can thrive.
• Support for reasonable adjustments during the recruitment process.