Quantitative Modeling Lead [Multiple Positions Available]

JPMorganChase•Jersey City, NJ

18h•Onsite

About The Position

This role involves conducting independent tests and developing benchmark models to evaluate performance. A key responsibility is assessing the risks associated with machine learning and deep learning models, identifying vulnerabilities, and recommending mitigation strategies. The position also requires drafting and reviewing documentation, mentoring junior team members, and staying current with AI/ML advancements. The Quantitative Modeling Lead will guide model developers and business partners on model risk governance, coordinate governance activities, and assess model design and implementation for alignment with risk and regulatory requirements. The role oversees the end-to-end model risk lifecycle, provides expert insights for model enhancements, and presents findings to senior management. Additionally, the position involves representing the team in audits and regulatory reviews, and supporting team development initiatives like recruiting and onboarding.

Requirements

Master's degree in Computational Science and Engineering, Quantitative & Computational Finance, Data Science, Machine Learning, Statistics, Mathematics, Computer Science, Computer Engineering or related field of study
2 years of experience in the job offered or as Quantitative Modeling Lead, Quantitative Analytics Associate, Quantitative Analyst, or related occupation.
Two (2) years of experience with performing model risk assessments of XGBoost models, including validation of statistical methods, hyper-parameters, and interpretability using Shap.
Two (2) years of experience conducting independent reviews of ML pipelines, validating feature engineering and selection processes, tuning methodologies, and evaluation frameworks using XGBoost, Scikit-learn, PyTorch, TensorFlow, and Keras.
Two (2) years of experience using algorithms, including linear and logistic regression, clustering, and CART to benchmark and analyze data.
Two (2) years of experience evaluating models using metrics including AUC-ROC, Precision-Recall, cross-entropy loss, and KS.
Two (2) years of experience developing models using Python, R, and SQL with object-oriented programming principles.
Two (2) years of experience manipulating data, including imputation, encoding, and normalization, using NumPy, Pandas, PySpark, and Dask.
Two (2) years of experience visualizing results with Matplotlib, Seaborn, and ggplot.
Two (2) years of experience optimizing large dataset computations with multithreading and multiprocessing in PySpark.
Two (2) years of experience managing data storage and processing with AWS.
Two (2) years of experience conducting analysis in graphical database using TigerGraph.

Responsibilities

Conduct independent tests and develop benchmark models that serve as reference points for evaluating model performance.
Evaluate the risks associated with machine learning and deep learning models by systematically identifying potential vulnerabilities and recommending mitigation strategies to minimize model risk.
Draft and review documentation related to model reviews.
Mentor and train junior team members, sharing best practices and supporting their professional development.
Stay current with advancements in AI/ML algorithms and fraud detection techniques, incorporating new insights and technologies into the model validation process.
Guide model developers and business partners through model risk governance requirements and processes.
Coordinate and lead governance activities for the team such as performance monitoring and the annual status assessment, to ensure ongoing model integrity and compliance.
Assess and challenge model design and implementation to ensure alignment with risk management and regulatory requirements.
Oversee the end-to-end model risk lifecycle, including validation, performance monitoring, change management, and issue remediation.
Provide expert insights and recommendations for model enhancements, and present findings to senior management and key stakeholders.
Represent the team in audit and regulatory reviews, ensuring timely and accurate responses to inquiries.
Support team development initiatives, including recruiting, hiring, and onboarding new team members.