Quantitative Trading & Research - SPG - Vice President

JPMorgan Chase & Co.•New York, NY

About The Position

The Securitized Products Group (SPG) Quantitative Trading & Research (QTR) team is a high-performing quantitative modeling organization focused on Residential Mortgage-Backed Securities (RMBS) and related structured products. The group develops and maintains agency and non-agency RMBS models and analytical tools used to support CIB trading and research. These prepayment and credit/default models also support RMBS and mortgage loan valuation and risk management across JPMorganChase, including the Mortgage Bank, Chief Investment Office, and Asset & Wealth Management. Selected analytics are delivered to external clients via OASis and BondStudio. As a Vice President in the Securitized Products Group (SPG) Quantitative Trading & Research Team (QTR), you will sit within the non-agency RMBS modeling team and partners closely with SPG trading desks to support modeling, valuation, market-making, and risk assessment. You will help drive the modernization of credit modeling by applying machine learning and generative AI across the model development lifecycle, including data processing and exploration, model calibration, performance monitoring, and delivery of analytics and reporting tools. You will collaborate with stakeholders across business, technology, market risk, and other partner teams to develop new models and enhance existing capabilities, improve understanding of model behavior and trading insights, ensure robust model infrastructure and controlled usage, and provide subject matter expertise, training, and guidance to internal users and external clients.

Requirements

Strong quantitative educational background: Master’s or PhD degree in a quantitative field.
Advanced modeling skills in developing machine learning (ML), statistical, or econometric models, preferably with applications in financial fields.
Strong programming skills in Python (C++ is a plus); proficiency in statistical Python packages such as NumPy, Pandas, and stats packages (StatsModels, scikit-learn, SciPy, etc.) for data manipulation and statistical analysis.
Experience working with large-scale databases (e.g., PostgreSQL, Redshift) for machine learning analysis and modeling is desirable.
Experience in data analysis focused on mortgage and loan performance datasets, specifically analyzing prepayment and credit historical data at the loan or facility level, is desirable.

Responsibilities

Develop and support advanced financial models for RMBS, enabling business portfolio management, trading, hedging, and risk assessment.
Conduct model back-testing, performance tracking, and provide business insights to inform portfolio management and trading strategies.
Perform large-scale data queries, processing, and machine learning (ML) analysis for RMBS prepayment and credit modeling using high-quality calibration data.
Build and optimize robust platforms for large-scale data analysis to support various modeling initiatives.
Develop new models and analytical tools, and implement them within our advanced, high-performing mortgage loan/bond pricing and analytics framework.
Design and implement analytical tools to monitor model performance and market conditions in Residential Mortgage-Backed Securities (RMBS), enhancing business decision-making processes.
Oversee the maintenance and enhancement of existing infrastructure used for valuation and hedging of financial transactions.
Provide support to internal and external clients regarding model usage, addressing inquiries and facilitating training as needed.
Collaborate closely with risk and model review groups to ensure proper model usage, conduct model reviews, and implement effective risk controls.