Eurowag is building a credit decisioning capability that will underpin credit risk lending decisions across multiple products and markets. This role is the core of that capability. The Credit Decisioning Analyst will own the monitoring of the risk decisions and how these decisions eventually affect the performance of the lending portfolio, translating data into insights for dynamic risk management.

This is not a maintenance role. We are at the start of the build. The person we hire will help define how credit decisions are made, implemented and monitored at Eurowag for the next several years.

Eurowag is transitioning from a commercial fuel card and payments business to a financial services platform serving road transport operators across Europe. We are implementing Experian PowerCurve as our decisioning engine.

In parallel, our new SVP of Data & AI is leading a company-wide modernization of data infrastructure. This role sits at the intersection of credit risk and data capability and will be a key contributor to that transformation. The platform and the data infrastructure we build now will determine our ability to scale products across new markets.

The Credit Decisioning Analyst we hire must be ready not just for today's pilot, but for what this platform becomes in the future. Strategy & Decision Logic

• Design, configure, and optimize credit decision strategies in the decision engine, including scorecards, rules, and cut-off logic
• Translate credit policy into automated decision flows, maintaining a live rule library with full version control and override governance
• Run champion-challenger/shadow deployments before any live approval change
• Own the feedback loop between observed vs predicted results

Model Development & Monitoring

• Contribute to the development of Risk database aligned with the Data & AI modernisation roadmap
• Identify scorecard degradation early and initiate recalibration or rebuild
• Desired- Build and validate application, behavioural and collections scorecards using logistic regression and machine learning approaches
• Desired- Monitor model performance on an ongoing basis: Gini, PSI, score drift, population stability

Analytics & Reporting

• Produce regular credit performance reporting and KPIs
• Build and maintain dashboards in Power BI or equivalent tools for credit risk KPIs
• Support IFRS 9 provisioning with PD/LGD segment-level inputs
• Conduct portfolio segmentation analysis to support portfolio management for limit review, watchlists and early warning system.
• Support collections with suggestions to optimize collections policies.

Stakeholder & Cross-functional Work

• Act as the primary analytical interface between credit risk and the Data & AI team
• Collaborate with collections leads on segmentation strategy and risk feedback loops
• Support the Head of Credit & Collections with credit committee materials and policy documentation
• Participate in Experian managed service handover, ensuring full knowledge transfer before go-live

Required

• Master's degree in mathematics, statistics, engineering, economics, or a quantitative field
• 3 to 5 years of experience in credit risk analytics at a bank, fintech, or credit bureau
• Strong Python or R skills; SQL is non-negotiable
• Experience working with a decisioning or credit management platform (PowerCurve, Provenir, FICO Blaze, Pega, or equivalent)
• Ability to work independently and own a problem end to end without close supervision

Strongly Preferred

• Experience in SME or commercial credit, or fleet/transport industry context
• Direct experience with Experian PowerCurve Strategy Management
• Experience in a multi-market or cross-border credit environment
• Hands-on scorecard development experience: logistic regression, WOE/IV binning, validation
• Exposure to feature engineering for credit models using transactional or behavioural data
• Familiarity with IFRS 9 impairment modelling and ECL frameworks

Personal Attributes

• Operates with a builder mindset: comfortable in ambiguity and early-stage environments
• Combines technical depth with commercial awareness
• Communicates findings clearly to non-technical audiences
• Takes ownership and escalates with a proposed solution, not just a problem
• Intellectually curious about how data and AI can extend credit risk capability