CCB Risk Program Associate

Testing Site - JPMC; Plano (TX); On-site; USD 90,000 - 150,000; Full time

Job summary

Chase is seeking a Risk program Senior Associate to advance fraud risk ranking of transactions and applications for new products. You will identify ML algorithms, perform feature engineering, and train models on vast datasets using modern tech stacks to improve fraud control and customer experience.

The role requires a Master’s in a quantitative field, 2 years in Python analytics, and experience with diverse ML techniques. A strong interest in model behavior and practical design is essential.

Qualifications

• Master's degree in Mathematics, Statistics, Economics, Computer Science, Operations Research, Physics, and other related quantitative fields.
• 2 years of experience with data analysis in Python.
• Some Experience in designing models for a commercial purpose using at least 3 of CNN, RNN, SVM, Reinforcement Learning, Random Forest/GBM.
• A strong interest in how models work and why they succeed or fail, and practical aspects of model design.

Responsibilities

• Identify and retool machine learning (ML) algorithms to analyze datasets for fraud detection in the Chase Consumer Bank.
• Perform ML tasks such as feature engineering, feature selection, and developing and training ML algorithms using cutting-edge technology to extract predictive models/patterns from billions of transactions’ data.
• Collaborate with business teams to identify opportunities, collect business needs, and provide guidance on leveraging the ML solutions.
• Interact with a broader audience in the firm to share knowledge, disseminate findings, and provide domain expertise.

Skills

Python data analysis

ML concepts

Fraud detection

Analytical thinking

Education

Master's degree (Math/Stats/CS/OR/Physics)

PhD in quantitative field

Tools

Spark

Hive

Keras/TensorFlow

Graph databases (Neo4j/Tig​erGraph)

PyTorch

Job description

Come and join us in reshaping the future

As a Risk program Senior Associate within the Chase consumer Bank, you'll be the analytical expert for identifying and retooling suitable machine learning algorithms that can enhance the fraud risk ranking of particular transactions and/or applications for new products. This includes a balance of feature engineering, feature selection, and developing and training machine learning algorithms using cutting edge technology to extract predictive models/patterns from data gathered for billions of transactions. Your expertise and insights will help us effectively utilize big data platforms, data assets, and analytical capabilities to control fraud loss and improve customer experience.

Job Responsibilities:

• Identify and retool machine learning (ML) algorithms to analyze datasets for fraud detection in the Chase Consumer Bank.


• Perform machine learning tasks such as feature engineering, feature selection, and developing and training machine learning algorithms using cutting-edge technology to extract predictive models/patterns from billions of transactions’ amounts of data.


• Collaborate with business teams to identify opportunities, collect business needs, and provide guidance on leveraging the machine learning solutions.


• Interact with a broader audience in the firm to share knowledge, disseminate findings, and provide domain expertise

Required qualifications, capabilities and skills:

• Master's degree in Mathematics, Statistics, Economics, Computer Science, Operations Research, Physics, and other related quantitative fields.


• 2 years of experience with data analysis in Python.


• Some Experience in designing models for a commercial purpose using some (at least 3) of the following machine learning and optimization techniques: CNN, RNN, SVM, Reinforcement Learning, Random Forest/GBM.


• A strong interest in how models work, the reasons why particular models work or not work on particular problems, and the practical aspects of how new models are designed.

Preferred qualifications, capabilities and skills:

• PhD in a quantitative field with publications in top journals, preferably in machine learning.


• Experience with model design in a big data environment making use of distributed/parallel processing via Hadoop, particularly Spark and Hive.


• Experience designing models with Keras/TensorFlow on GPU-accelerated hardware.


• Experience with graph technology, including designing and implementing graph-based machine learning models for fraud detection or risk assessment. Familiarity with graph databases (such as TigerGraph or Neo4j ...), graph algorithms (e.g., node classification, link prediction, community detection), and graph feature engineering is highly desirable. Ability to leverage graph analytics to uncover complex relationships and patterns within large-scale transaction data is a strong plus.


• Hands‑on experience with transformer models and related architectures (such as BERT, GPT, or Graph Transformers) for natural language processing, anomaly detection, or transaction analysis. Proficiency in fine-tuning and deploying transformer‑based models using frameworks like PyTorch or TensorFlow is preferred. Demonstrated ability to apply transformer models to extract meaningful insights from unstructured or semi‑structured data sources will be highly valued.