Model Developer [Multiple Positions Available]

JPMorganChase•Jersey City, WA

1d•Onsite

About The Position

This role involves overseeing the daily calculation of Average Daily Trading Volume, addressing analytical issues, and ensuring the timely delivery of high-quality data for setting Counterparty Credit Risk limits. The position requires leading implementation projects, reviewing code, and mentoring junior developers. A key responsibility is developing and maintaining advanced models, methodologies, and infrastructure for anomaly detection in time series data, including flats, spikes, liquidity deficiencies, and data integrity issues, along with implementing data remediation techniques. The role also focuses on analyzing and improving the performance of outlier detection and missing data imputation tools, enhancing the analytics framework of the Data Quality Program for market data time series, and supporting firmwide Value at Risk models across multiple asset classes. Additionally, the position involves developing, maintaining, and enhancing APIs and visualization tools for time series data management and analysis, designing a scalable framework for onboarding new data sources, and creating data quality metrics and KPIs to assess data quality, identify trends, and communicate findings to senior management. Responding to audit requests and understanding methodologies to debug implementation code for data lineage and synthetic time series derivation are also part of the duties.

Requirements

Developing numerical programs for financial time series analytics using Python and Python libraries including NumPy, Pandas, SciPy, Seaborn, and Matplotlib to process, model, and visualize market data
Building and optimizing SQL queries to extract, transform, and analyze financial time series data from multiple sources
Applying dependency graph programming techniques to manage and process relationships within market data
Designing statistical models to detect data anomalies and ensure integrity in financial datasets, utilizing techniques including correlation analysis, linear regression, and outlier detection algorithms
Performing data engineering and remediation using quantitative methods, including numerical calculus, linear interpolation, non-linear interpolation, and proxy filling
Developing scalable data lake storage solutions with integrated analytical frameworks using object-oriented design and distributed computing to extract, transform, and analyze data used for risk modeling and calculation
Enhancing core calculation frameworks through code optimization and performing code review, unit testing, and regression testing while adhering to best coding practices for production deployment
Supporting pricing, risk calculations and derived time series construction across Equities, Fixed Income, FX, Commodities, and Structured Products asset classes using financial product knowledge of futures, options, credit default swaps, and securitized products
Estimating financial instrument profit and loss and conducting VaR impact analysis using VaR modeling methods including variance covariance, historical simulation, and Monte Carlo simulation, and sensitivity analysis using delta, gamma, vega, theta, and cross-terms
Creating key performance metrics by applying statistical analysis to measure the significance of data quality issues affecting risk measurements

Responsibilities

Oversee the daily calculation of Average Daily Trading Volume and address analytical issues to ensure the timely delivery of high-quality data essential for setting Counterparty Credit Risk limits.
Lead implementation projects by overseeing analytical work and reviewing code produced by junior developers.
Coach and mentor junior team members and help develop their quantitative and technical skills.
Develop and maintain advanced models, methodologies and infrastructure to detect anomalies in time series data, such as flats, spikes, as well as issues related to deficiency in liquidity and data integrity and implement data remediation techniques.
Analyze and improve the performance of outlier detection and missing data imputation tools.
Enhance the analytics framework of the Data Quality Program for market data time series, supporting firmwide Value at Risk models across multiple asset classes.
Develop, maintain and enhance APIs and visualization tools used for time series data management and analysis.
Design and develop a scalable framework that can easily onboard new data source while adapting to evolving analytics needs.
Create data quality metrics and KPIs to assess data quality, identify trends and areas for improvement, and communicate findings to senior management and internal control functions.
Respond to audit requests from external and internal audits, regulatory exams, and risk control managers.
Understand methodologies and debug implementation code to establish data lineage and identify issues in the derivation of synthetic time series generated from raw time series data.