Evening Amazon Data Science Jobs in Delaware (NOW HIRING)

Bring your expertise to JPMorgan Chase. As part of Risk Management and Compliance, you are at the center of keeping JPMorgan Chase strong and resilient. You help the firm grow its business in a responsible way by anticipating new and emerging risks, and using your expert judgement to solve real-world challenges that impact our company, customers and communities. Our culture in Risk Management and Compliance is all about thinking outside the box, challenging the status quo and striving to be best-in-class.
As a Vice President - Credit Risk Data Science, Business Banking Risk Modeling, you will lead advanced feature engineering and machine learning initiatives that power customer analytics and credit risk decisioning across Chase sub-lines of business. You will own the end-to-end design and scaling of an enterprise Risk Attribute Library, ensuring feature quality, lineage, and reusability, while building and improving production-grade models that influence critical business decisions. Starting with a focus on the card business, you will extend solutions across the broader Chase portfolio and drive innovation using modern analytics, deep learning, and large language model enabled approaches.

• Lead the design, development, and governance of a scalable enterprise Risk Attribute Library, owning end-to-end attribute and model quality.
• Drive consistency, reliability, and reuse of features across customer lifecycles and Chase sub-lines of business through rigorous standards and reproducible development practices.
• Partner with cross-functional teams to ideate, prototype, and productionize advanced feature engineering methods.
• Engineer high-impact features from large-scale structured and unstructured datasets to improve predictive performance and decisioning outcomes.
• Build robust machine learning and deep learning models, including Transformer-based approaches, to predict customer behavior and optimize risk strategies.
• Apply large language model techniques to extract signal from unstructured text (for example, customer interactions, disclosures, narratives) to enhance models and enable new analytics products.
• Establish attribute quality testing and monitoring frameworks to detect data drift, leakage, instability, and distribution shifts.
• Implement alerting mechanisms and resolve data or feature issues to maintain accuracy, stability, and consistency in production.
• Evaluate new internal and external data sources by assessing signal strength, stability, latency, and compliance considerations.
• Align with risk, marketing, technology, data governance, and controls partners to ensure correct implementation and robust documentation, lineage, and lifecycle management.
• Communicate complex analytical findings clearly to technical and non-technical stakeholders, translating results into actionable recommendations and measurable business impact.
  

• Master's degree or Doctor of Philosophy degree in Computer Science, Mathematics, Statistics, Econometrics, Engineering, or a related quantitative discipline.
• 5+ years of experience working with large-scale data and developing, managing, or implementing attributes and predictive models.
• 5+ years of professional coding experience with demonstrated ability to write high-quality, production-ready code.
• Proficiency in one or more of the following: Python, Statistical Analysis System, Apache Spark, Scala, or equivalent data and machine learning programming stacks.
• Experience with modern machine learning and deep learning frameworks and platforms such as TensorFlow (or equivalent), Amazon Web Services cloud, Snowflake, and or Databricks.
• Strong understanding of statistical and machine learning methods such as generalized linear models and regression, decision trees, random forests, boosting, clustering, k-nearest neighbors, anomaly detection, simulation, scenario analysis, and modeling.
• Demonstrated ability to perform feature engineering, model validation, and performance evaluation in a regulated or controlled environment.
  

• consumer lending experience strongly preferred