Our Consumer Bank AI Modeling team develops advanced analytics and machine learning solutions that inform high-impact decisions across field workforce effectiveness, customer engagement, and banker-led growth.
As an Applied AI Modeling Vice President in the Consumer Bank AI Modeling team, you will build and deploy advanced AI/ML models that measurably improve banker sales effectiveness and customer outcomes. Your models will help bankers deliver the right outreach at the right time to our customers, driving deposit growth, increasing customer retention, and strengthening relationships. You will operate in a highly governed environment and partner closely with product, UX, operations, and technology teams to translate modeling innovation into field-ready tools that bankers trust and adopt.
Job responsibilities
- Develop and launch AI/ML models that solve complex, ambiguous business problems in Consumer Banking, with emphasis on sales effectiveness and banker enablement (e.g., lead scoring, propensity modeling, next-best-action/next-best-offer, customer prioritization, retention, and cross-sell) using techniques such as deep learning, causal inference, contextual bandits, reinforcement learning, and constrained optimization.
- Lead modeling engagements end-to-end, including scoping use cases with business partners, defining success metrics (incrementality, ROI, adoption), building project plans, and working with large, complex datasets to formulate testable hypotheses.
- Translate model outputs into clear, actionable recommendations for non-technical partners, and produce narratives that drive adoption (why this lead, why now, what action, expected outcome).
- Partner with governance, risk, and controls teams to expedite fair and thorough model reviews, document model intent and limitations, monitor performance and drift, and maintain adherence to regulatory and model risk management standards.
Required qualifications, capabilities, and skills
- Master's or Ph.D. in a quantitative discipline such as Computer Science, Statistics, Machine Learning, Econometrics, Operations Research, Applied Mathematics, or a related field.
- 4+ years of hands-on, relevant industry experience developing and deploying AI/ML models in production, including statistical modeling and modern Machine Learning.
- Proficient in Python with hands-on experience in ML/deep learning frameworks (TensorFlow, PyTorch) and core libraries (NumPy, Scikit-Learn, Pandas). Strong working knowledge of notebooks and cloud-based development/compute.
- Deep expertise in at least one of the following, with meaningful exposure to at least one other, recommendation/decisioning systems (next-best-action/offer), ranking, and constrained optimization, causal inference and uplift / treatment effect modeling for targeted interventions, online learning approaches (contextual bandits, multi-armed bandits, reinforcement learning), behavioral modeling and human-in-the-loop systems that drive adoption and performance, and demonstrated ability to communicate complex modeling concepts clearly to non-technical stakeholders and drive decisions.
Preferred qualifications, capabilities, and skills
- Ph.D. in a relevant discipline.
- Experience developing advanced AI/ML models in consumer finance, fintech, retail, marketplaces, or other high-scale customer engagement environments.
- Experience with at least one of the following, decisioning/online learning libraries (e.g., Vowpal Wabbit, RLlib, Stable Baselines) or large-scale ranking/recommendation tooling, causal inference tooling and experimentation platforms (A/B testing, CUPED, synthetic controls, causal forests, doubly robust methods)
- Familiarity with behavioral science concepts (choice architecture, friction, habit formation) and designing interventions that are effective and compliant.
- Experience with Databricks, Snowflake, or similar platforms; strong practical MLOps experience (model deployment patterns, monitoring, drift detection, retraining, and reproducibility).