Data Scientist

Clara is the leading platform in Latin America for companies to execute and manage every payment operation. More than 50,000 leading and fast-growing businesses run on our corporate cards, bill pay, financing and B2B payments, and in 2025 the Financial Times named Clara the region’s fastest-growing company. We’re passionate about helping every company we work with become more effective—and, through that, raising the region’s competitiveness. We’re ~400 people, backed by Notable Capital, Coatue, Kaszek, monashees, DST Global, ICONIQ, General Catalyst and Goldman Sachs, among others.

What you'll do
We're looking for a Senior Data Scientist – Risk Modeling to join Clara’s Risk Data Science team. In this role, you will combine advanced analytics, machine learning, and credit risk expertise to develop and improve models and strategies that support underwriting, portfolio management, and risk decision-making across Clara’s markets.
You will work closely with Risk, Data, Engineering, Finance, and Operations, taking analytical problems from exploration and model development through validation, monitoring, and business implementation.
Your responsibilities will include:

• Develop credit risk models: Design, build, validate, and maintain predictive models for credit origination, behavioral risk, portfolio management, and other risk use cases.
• Own the modeling lifecycle: Work across the full model lifecycle, including problem definition, population and target construction, feature engineering, model development, validation, backtesting, calibration, monitoring, and recalibration.
• Drive advanced risk analytics: Use SQL and Python to explore large datasets, identify portfolio trends, analyze delinquency and losses, and translate findings into actionable risk strategies.
• Strengthen credit decisioning: Support the development and optimization of underwriting strategies, score cutoffs, credit limits, segmentation, and portfolio management policies.
• Monitor model and portfolio performance: Build monitoring frameworks to track model discrimination, calibration, stability, data drift, portfolio trends, vintages, roll rates, delinquency, and other key risk indicators.
• Improve data and modeling quality: Validate data sources, implement data quality controls, assess feature stability, and identify potential issues such as leakage, selection bias, or population drift.
• Work with rejected and unobserved populations: Contribute to methodologies for addressing where relevant.