APPLIED DATA SCIENTIST, FRAUD PREVENTION
£55,000 - £65,000
LONDON (HYBRID)
This is an exciting opportunity to join a growing FinTech with an innovative approach to lending. You'll play a key role in building and improving fraud prevention capabilities, working on high-impact machine learning projects that directly influence customer outcomes, risk strategy, and business performance.
THE COMPANY
Our client is a forward-thinking FinTech with a people-focused culture that prioritises teamwork and continuous development. Data is at the heart of their decision-making, and they are continuing to invest in advanced analytics to support growth and innovation. This role sits within a collaborative data science team where you will have the opportunity to make a tangible impact from day one.
THE ROLE
* Develop and deploy fraud detection, identity verification, and fraud scoring models
* Analyse large and complex datasets to identify fraud trends, risks, and opportunities
* Evaluate new data sources, machine learning techniques, and fraud prevention tools
* Build monitoring and reporting solutions to track model and fraud performance
* Collaborate with Product, Engineering, Risk, and Data teams to deliver business-critical initiatives
* Help shape the future direction of fraud analytics across the organisation
YOUR SKILLS AND EXPERIENCE
* Strong commercial experience in fraud analytics, fraud prevention, or financial crime
* Hands-on experience developing machine learning models using Python
* Strong SQL and data analysis capabilities
* Knowledge of statistical modelling and predictive analytics techniques
* Excellent communication skills with the ability to influence stakeholders
* Experience within fintech, lending, or financial services would be beneficial
SALARY AND BENEFITS
* £55,000 - £65,000 base salary depending on experience
* Annual bonus scheme
* Contributory pension
* Private healthcare
* Hybrid working model - 2 days in office
HOW TO APPLY
Please register your interest by sending your CV through the 'Apply' link.
:quality(80))
:quality(80))
:quality(80))