DVP - Secured Risk

This critical role acts as a bridge between technical modeling and business execution. The successful candidate will perform micro-level portfolio analysis, track emerging delinquency patterns, and formulate credit risk strategies. By partnering with Data Science, Product, and Engineering teams, the role ensures that predictive risk models and alternative data streams are optimally deployed to drive safe, profitable asset growth across various secured lending products.

Responsibilities:

• Portfolio Analytics and Delinquency Tracking: Conduct continuous, granular portfolio analytics and monitor delinquency trends at a micro-level. Identify and isolate performance indicators across distinct segments to isolate risk drivers and spot growth opportunities.
• Lifecycle Credit Strategy Development: Lead the creation, evaluation, and refinement of data-driven credit strategies across the entire customer lifecycle, including automated customer acquisition, portfolio limit management, fraud containment, and automated collection triggers.
• Trend Identification and Reporting: Uncover underlying portfolio behaviors and macro trends by executing complex data cuts and rigorous statistical validation, delivering actionable risk intelligence to support internal and leadership portfolio reviews.
• Cross-Functional Strategy Implementation: Collaborate extensively with the Product and Engineering teams to map out risk strategies, policy rules, and decisioning workflows, ensuring seamless implementation into the production environment.
• Model Optimization and Score Cut-Offs: Partner directly with the Data Science team to provide crucial domain expertise on key model variables, validate predictive performance, and dynamically optimize scorecard cut-offs for various proprietary risk models.
• Data Source Evolution and Alternative Underwriting: Develop an exhaustive knowledge of traditional (credit bureau) and alternative/digital data streams. Innovate optimal configurations for incorporating these diverse sources to enhance predictive accuracy.
• Product Architecture Alignment: Maintain a robust functional understanding of secured lending products (e. g., home loans and LAPs in both prime and affordable segments) to ensure risk frameworks perfectly align with business margins and product design.

Requirements:

• Educational Background: Bachelor's or Master's degree in Computer Science, Engineering, Statistics, Applied Mathematics, or a highly quantitative discipline from a premier institution
• Professional Experience: 8+ years of professional experience within data science, risk analytics, or quantitative risk management. Proven experience building predictive models, optimizing credit policies, and delivering complex analytical insights.
• Technical and Tool Proficiency: Advanced mastery of SQL for complex data extraction, querying, and manipulation. Strong hands-on programming proficiency in Python or R for statistical analysis and machine learning.
• Statistical Expertise: Deep conceptual and practical understanding of advanced statistical foundations, including descriptive analytics, experimental design, hypothesis testing, Bayesian inference, confidence intervals, and probability distributions.
• Machine Learning and Data Mining: Proficiency with core machine learning techniques and statistical algorithms, specifically decision tree learning, ensemble methods (Random Forest and Gradient Boosting), logistic regression, and cluster analysis.
• Data Dexterity: Demonstrated competence in processing, clean-up, and engineering of large-scale datasets, with a proven ability to work with both highly structured financial databases and semi-structured/unstructured data sources.
• Domain Expertise: Deep functional knowledge of retail credit lines and secured credit products. Exposure to fintech lending ecosystems, retail banking, NBFC operations, or SME/LAP/secured lending is strongly preferred.