Quantitative Model Developer Jobs in Texas (NOW HIRING)

SoFi is seeking a Fraud Model Developer to join our Fraud Model Development team. In this role, you will develop, evaluate, and monitor machine learning models that support data-driven fraud and risk decisions across SoFi's products and services, including Personal Loans, Student Loans, Credit Cards, and Crypto.

You will build quantitative and machine learning solutions designed to reduce fraud losses, minimize false positives, lower operational costs, and protect SoFi members. You will also analyze model and product performance, identify key drivers of fraud losses, and translate complex findings into actionable recommendations for business and risk partners.

This role requires strong experience in machine learning, statistical modeling, data analysis, and model performance monitoring. You will work closely with Fraud Risk, Fraud Operations, Product, Engineering, Finance, Accounting, and other business teams to develop scalable fraud-modeling solutions and ensure model performance and loss trends are clearly communicated.

• Develop quantitative, statistical, and machine learning models that reduce fraud losses, minimize false positives, and lower operational expenses associated with fraud complaints and disputes.
• Aggregate, clean, and synthesize large datasets from multiple data environments to support model development and analysis.
• Analyze complex datasets to identify fraud patterns, product-performance trends, and key drivers of losses across SoFi's products.
• Design, test, validate, and recalibrate fraud models using appropriate statistical and machine learning methodologies.
• Monitor model performance and identify model degradation, data drift, or changes in fraud behavior.
• Conduct fraud-loss forecasting, sensitivity analyses, and scenario-based assessments to evaluate potential business impact.
• Automate recurring model-monitoring processes, analytical reporting, and dashboards.
• Investigate external risk data and industry trends to identify emerging fraud patterns and modeling opportunities.
• Partner with Engineering and machine learning platform teams to support model implementation and production deployment.
• Collaborate with Business Units, Operations, Product, Capital Markets, Finance, Accounting, and Risk partners to communicate fraud-loss expectations, model performance, and emerging trends.
• Translate technical model results into clear recommendations that improve fraud strategies, member experiences, and operational outcomes.
• Maintain model documentation and support ongoing model governance, validation, and performance-review activities.

• Five or more years of experience in fraud modeling, loss forecasting, advanced quantitative modeling, machine learning, or a related field.
• A master's or doctoral degree in Statistics, Mathematics, Economics, Engineering, Computer Science, or another quantitative field, or equivalent relevant professional experience.
• Advanced proficiency in Python and SQL for data analysis, feature development, and machine learning model development.
• Experience creating analytical reports or dashboards using Tableau or a comparable data-visualization platform.
• Demonstrated experience developing and evaluating statistical and machine learning models, including methods such as linear regression, logistic regression, decision trees, gradient boosting, random forests, neural networks, or clustering.
• Hands-on knowledge of fraud-loss forecasting, fraud-reduction methodologies, or comparable risk-modeling techniques.
• Experience monitoring model performance and recalibrating models in response to performance changes, data drift, or evolving business conditions.
• Strong analytical and problem-solving skills, with the ability to evaluate complex datasets and communicate meaningful conclusions.
• Ability to translate model results into measurable business outcomes, including fraud-loss reduction, false-positive improvement, member-friction reduction, or operational savings.
• Demonstrated ability to work collaboratively across technical and nontechnical teams in a complex, fast-moving environment.
• A proactive approach to identifying problems, driving change, learning new methodologies, and taking ownership of results.

• Experience developing fraud models within financial services, fintech, banking, lending, payments, or digital assets.
• Familiarity with graph databases, graph analytics, or network-based fraud-detection methods.
• Experience developing, deploying, or productionizing machine learning models in an AWS environment.
• Familiarity with machine learning operations, model governance, or automated model-monitoring frameworks.