Senior Data Scientist

Cashera is a fast-growing fintech and lending company that provides funding solutions to businesses across multiple industries in the United States. Cashera combines technology, data-driven decision-making, and industry expertise to deliver fast, flexible financing options that traditional lenders often cannot provide.

The Role

As a Senior Data Scientist on the Credit & Fraud Risk Team, you will take ownership of the end-to-end lifecycle of predictive machine learning models. You'll play a foundational role in building systems that evaluate borrower creditworthiness, mitigate operational loss, and intercept real-time fraud vectors. This is a business-critical position reporting directly to Risk and Data Science Leadership, collaborating closely with Engineering, Product, Collections, and Finance teams.

Key Responsibilities

• Model Development & Lifecycle: Build, evaluate, and scale predictive models using XGBoost, LightGBM, and Deep Learning for underwriting, credit line assignment, and collections. Familiarity with gen-AI techniques for feature creation and transaction tagging on bank transactional data is a plus.
• Credit Risk Modeling: Build credit risk models for sub-prime and near-prime customers in a fintech environment with short model build cycles.
• Fraud & Risk Defense: Design and deploy real-time decisioning rules and ML systems to detect synthetic fraud, digital identity theft, account takeovers, and transactional fraud.
• Feature Engineering: Mine complex, large-scale, and alternative data streams (bank transactional data, logs, credit bureau reports, structured/unstructured digital signals) to extract predictive signals.
• Portfolio Optimization: Partner with Credit Risk Strategists to translate model outputs into actionable credit limits, cutoff thresholds, and loss-forecasting simulations.
• Platform Architecture: Collaborate with Data Platform Engineers to build reliable pipelines and high-throughput feature extraction.
• Leadership & Communication: Raise the technical bar through peer reviews, reusable tooling, and pro-active communication to risk leadership and partners.

What You'll Bring

• Education: Advanced degree (M.S. or Ph.D.) in a quantitative field (Statistics, Mathematics, Computer Science, Economics, Data Science) or equivalent practical experience.
• Experience: 4–6 years of Data Science experience, ideally including 3+ years focused on Credit Risk, Fraud Analytics, Lending, or Fintech.
• Technical Toolbox: Production-grade fluency in Python and advanced, highly analytical SQL.
• Modern Stack Experience: Hands-on experience scaling data workflows over frameworks like Snowflake, Databricks, Spark, dbt, or similar platforms.
• Business Communication: Ability to clearly present complex results (e.g., ROC-AUC curves, model drift scenarios) to non-technical stakeholders.