Manager 2, Data Science

About the Role

Key Responsibilities

• Develop market leading statistical models for the risk department producing risk scores, collections scores, fraud models, probability of defaults, and enhancing underwriting and risk performance for consumer lending solutions.
• Build predictive models, segmentation frameworks, and advanced experimentation methods, draw conclusions on the impact of product experiences, and communicate results to peers and leaders to measure and optimize data-driven strategies in emerging areas of the consumer lending roadmap.
• Provide technical guidance to the team to utilize models and develop advanced experimentation methods, including traditional and new AI/ML techniques.
• Partner closely with credit and fraud risk policy teams to influence the roadmap, monitor performance and effectiveness of strategies, and maintain a thorough understanding of risk, operational, and product concepts to manage major portfolio risk factors.
• Create and manage multiple modeling scorecard initiatives and support the growth and scalability of consumer lending products.
• Drive strategic thinking and cross-functional alignment around data-driven approaches to optimize the lending funnel.

Requirements

• At least 10+ years of experience in data science or a related field, with a strong background in leading complex, cross-functional projects and driving data-driven decision-making.
• Preferred experience in lending or fintech domain.
• 5+ years of experience building and leading high-performing teams, mentoring, and collaborating with executives and other teams to drive impact.
• Excellent communication skills with the ability to articulate complex data science concepts to non-technical stakeholders.
• Strong business and product sense, with the ability to shape vague questions into well-defined analyses and success metrics.
• Deep expertise in customer behavior analytics, predictive modeling, segmentation, and experimentation beyond A/B testing.
• Experience with AI tools is a plus.
• Domain experience in FinTech, Risk, Financial services, especially in Consumer Lending, is highly advantageous.
• PhD in quantitative fields such as Statistics, Mathematics, Computer Science, or Machine Learning.
• Experience in developing statistical models for risk scores, collections, fraud, and other credit-related solutions.
• Knowledge of traditional model development techniques (e.g., linear and logistic regression) and AI/ML techniques (e.g., gradient boosting, random forests, clustering).
• Ability to investigate escalated incidences in reports to drive business optimization.

Nice to Have

• Experience with AI tools.
• Specific expertise in Consumer Lending within FinTech.

Qualifications

• PhD in Statistics, Mathematics, Computer Science, or Machine Learning.