Engineering-New York-Vice President, Quantitative Engineering-10427773

Goldman Sachs•New York, NY

22h•$191,000 - $236,800•Onsite

About The Position

Lead the design, development, implementation, and documentation of advanced quantitative models and scenarios for time series forecasting. Incorporate economic, financial, and business-risk variables to address practical issues in finance and risk management and conduct uncertainty quantification. Develop and deploy explainable Machine Learning (ML) models for event prediction and risk scoring. Derive actionable insights to support business strategy, regulatory compliance, and internal governance reviews. Collaborate with cross-functional stakeholders across business divisions, Finance and risk departments. Translate complex user needs into precise model specifications, analytical metrics, interactive dashboards, and comprehensive reports. Execute the end-to-end model development lifecycle, encompassing data collection, exploratory data analysis, feature engineering, variable selection, model selection, hyperparameter tuning, validation, and scalable cloud-based deployment. Design and engineer Artificial Intelligence (AI) agentic systems to deliver analytical, data science, and reporting capabilities through conversational interfaces. Manage agent orchestration, context management, knowledge base integration, and overall AI lifecycle management. Conduct rigorous simulation studies, provide theoretical justifications, and perform model performance testing. Create and maintain comprehensive technical documentation to support Model Risk Management reviews, facilitate finding remediation, and ensure ongoing model monitoring.

Requirements

PhD degree (U.S. or foreign equivalent) in Mathematics, Computer Science, Financial Engineering, Applied Mathematics, or related quantitative field such as Statistics and one (1) year of experience in job offered or a related quantitative engineering role OR Master’s degree (U.S. or foreign equivalent) in Mathematics, Computer Science, Financial Engineering, Applied Mathematics, or related quantitative field such as Statistics and three (3) years of experience in job offered or a related quantitative engineering role OR Bachelor’s degree (U.S. or foreign equivalent) in Mathematics, Computer Science, Financial Engineering, Applied Mathematics, or related quantitative field such as Statistics and five (5) years of experience in job offered or a related quantitative engineering role.
Prior experience must include one (1) year with PhD OR three (3) years with Master’s OR five (5) years with Bachelor’s with the following:
programming Languages including C++, R, or Python
econometrics and Time-Series Analysis including modern time-series econometric techniques for forecasting, structural-break analysis, and regime-switching analysis
simulation and Uncertainty Quantification including Monte Carlo simulation and modern Conformal Prediction methods for uncertainty quantification
machine Learning and non-parametric statistics including statistical learning methods with emphasis on explainable ML, causal model selection, and hyperparameter tuning
production Cloud Deployment including implementation of mathematical and statistical models in scalable, production-grade cloud environments
data Management including management and processing of large-scale structured and unstructured datasets using database query languages and data management tools
model Validation and Documentation including design and execution of simulation studies, validation and theoretical justification, and production of comprehensive model risk documentation to support independent Model Risk Management (MRM) validation
AI Agent Development including common agentic framework and context management, harness engineering, multi-agent orchestration, knowledge base integration, and safe code execution.

Responsibilities

Lead the design, development, implementation, and documentation of advanced quantitative models and scenarios for time series forecasting.
Incorporate economic, financial, and business-risk variables to address practical issues in finance and risk management and conduct uncertainty quantification.
Develop and deploy explainable Machine Learning (ML) models for event prediction and risk scoring.
Derive actionable insights to support business strategy, regulatory compliance, and internal governance reviews.
Collaborate with cross-functional stakeholders across business divisions, Finance and risk departments.
Translate complex user needs into precise model specifications, analytical metrics, interactive dashboards, and comprehensive reports.
Execute the end-to-end model development lifecycle, encompassing data collection, exploratory data analysis, feature engineering, variable selection, model selection, hyperparameter tuning, validation, and scalable cloud-based deployment.
Design and engineer Artificial Intelligence (AI) agentic systems to deliver analytical, data science, and reporting capabilities through conversational interfaces.
Manage agent orchestration, context management, knowledge base integration, and overall AI lifecycle management.
Conduct rigorous simulation studies, provide theoretical justifications, and perform model performance testing.
Create and maintain comprehensive technical documentation to support Model Risk Management reviews, facilitate finding remediation, and ensure ongoing model monitoring.