Ccb Risk Program Associate

JPMorgan Chase · Banking · Wilmington, DE +1 · Consumer & Community Banking

Develops and deploys machine learning models, including deep learning and LLMs, for fraud detection and prevention across the customer lifecycle within a financial services context. Requires strong quantitative background, hands-on experience with LLM APIs and ML libraries, and expertise in model development, deployment, and interpretability.

What you'd actually do

Design and develop machine learning models to drive impactful fraud modeling, covering the entire customer lifecycle, including acquisition, account management, transaction authorization, and collections.
Apply state-of-the-art machine learning methodologies — including deep learning architecture, transformer-based models, and LLMs — on big data platforms to tackle complex business challenges.
Work closely with senior management to develop and implement ambitious, innovative modeling solutions, ensuring their successful deployment into production environments.
Collaborate with diverse teams, including risk, technology, model governance, and research, throughout the entire modeling lifecycle—from development and review to deployment and operational use.

Skills

Required

Ph.D. or Master’s degree in a quantitative discipline (Computer Science, Mathematics, Statistics, Econometrics, or Engineering)
5+ years of experience in creating predictive models and generative AI solutions using LLM prompt engineering
Hands-on experience with LLM APIs
Proficiency in Python libraries (Pandas, NumPy, scikit-learn)
In-depth knowledge of advanced machine learning algorithms (logistic regression, XGBoost, Deep Neural Networks, clustering, recommendation systems)
Expertise in model design, hyperparameter tuning, and responsible deployment practices
Experience in model interpretability and explainability
Familiarity with LLMs, fine-tuning, prompt engineering, and responsible deployment
Proficiency in Python, TensorFlow, PyTorch, Spark, or Scala
Experience with big data technologies (Hadoop, AWS, Hive)
Familiarity with MLOps tooling (model monitoring, drift detection, auditability)

Nice to have

Experience extending interpretability methods to deep learning architectures (CNNs, RNNs, transformers)
Strong expertise, interest, and track record of performing cutting-edge research on Gen-AI
Demonstrated expertise in data wrangling and model building on a distributed Cloud computation environment
GPU experience

What the JD emphasized

Ph.D. or Master’s degree from a reputable institution in a quantitative discipline
5+ years' experience in creating predictive models, and generative AI solutions using LLM prompt engineering
Hands-on experience with LLM APIs
In-depth knowledge of advanced machine learning algorithms
Demonstrated experience in model interpretability and explainability
Familiarity with large language models (LLMs) and their applications, including experience in fine-tuning, prompt engineering, and responsible deployment with appropriate safeguards, monitoring, and auditability.
Proficiency in Python, TensorFlow, PyTorch, Spark, or Scala, coupled with experience in big data technologies such as Hadoop, AWS, and Hive, and familiarity with MLOps tooling that supports model monitoring, drift detection, and end-to-end auditability.
Proven track record in designing, building, and deploying high-quality machine learning models in production environments

Other signals

fraud modeling
LLM prompt engineering
deploying models in production

Read full job description

Key Responsibilities

Model Development: Design and develop machine learning models to drive impactful fraud modeling, covering the entire customer lifecycle, including acquisition, account management, transaction authorization, and collections.
Advanced Machine Learning Techniques: Apply state-of-the-art machine learning methodologies — including deep learning architecture, transformer-based models, and LLMs — on big data platforms to tackle complex business challenges.
Strategic Collaboration: Work closely with senior management to develop and implement ambitious, innovative modeling solutions, ensuring their successful deployment into production environments.
Cross-Functional Partnership: Collaborate with diverse teams, including risk, technology, model governance, and research, throughout the entire modeling lifecycle—from development and review to deployment and operational use.

Basic Qualifications

Ph.D. or Master’s degree from a reputable institution in a quantitative discipline such as Computer Science, Mathematics, Statistics, Econometrics, or Engineering.
5+ years' experience in creating predictive models, and generative AI solutions using LLM prompt engineering.
Hands-on experience with LLM APIs, Python libraries like Pandas, NumPy, scikit-learn, and others for data manipulation, modeling and analysis.
In-depth knowledge of advanced machine learning algorithms, including logistic regression, XGBoost, Deep Neural Networks (CNN and RNN), clustering, and recommendation systems, with expertise in model design, hyperparameter tuning, and responsible deployment practices.
Demonstrated experience in model interpretability and explainability for complex models such as XGBoost and GBM; experience extending these methods to deep learning architectures (CNNs, RNNs, transformers) is a strong plus.
Familiarity with large language models (LLMs) and their applications, including experience in fine-tuning, prompt engineering, and responsible deployment with appropriate safeguards, monitoring, and auditability.
Proficiency in Python, TensorFlow, PyTorch, Spark, or Scala, coupled with experience in big data technologies such as Hadoop, AWS, and Hive, and familiarity with MLOps tooling that supports model monitoring, drift detection, and end-to-end auditability.

Preferred Qualifications

Strong expertise, interest, and track record of performing cutting-edge research on Gen-AI
Proven track record in designing, building, and deploying high-quality machine learning models in production environments, demonstrating a strong ability to translate theoretical concepts into practical applications.
Demonstrated expertise in data wrangling and model building on a distributed Cloud computation environment (with stability, scalability and efficiency). GPU experience is desired.
Strong ownership and execution; proven experience in implementing models in production.

Key Responsibilities

Model Development: Design and develop machine learning models to drive impactful fraud modeling, covering the entire customer lifecycle, including acquisition, account management, transaction authorization, and collections.
Advanced Machine Learning Techniques: Apply state-of-the-art machine learning methodologies — including deep learning architecture, transformer-based models, and LLMs — on big data platforms to tackle complex business challenges.
Strategic Collaboration: Work closely with senior management to develop and implement ambitious, innovative modeling solutions, ensuring their successful deployment into production environments.
Cross-Functional Partnership: Collaborate with diverse teams, including risk, technology, model governance, and research, throughout the entire modeling lifecycle—from development and review to deployment and operational use.

Basic Qualifications

Ph.D. or Master’s degree from a reputable institution in a quantitative discipline such as Computer Science, Mathematics, Statistics, Econometrics, or Engineering.
5+ years' experience in creating predictive models, and generative AI solutions using LLM prompt engineering.
Hands-on experience with LLM APIs, Python libraries like Pandas, NumPy, scikit-learn, and others for data manipulation, modeling and analysis.
In-depth knowledge of advanced machine learning algorithms, including logistic regression, XGBoost, Deep Neural Networks (CNN and RNN), clustering, and recommendation systems, with expertise in model design, hyperparameter tuning, and responsible deployment practices.
Demonstrated experience in model interpretability and explainability for complex models such as XGBoost and GBM; experience extending these methods to deep learning architectures (CNNs, RNNs, transformers) is a strong plus.
Familiarity with large language models (LLMs) and their applications, including experience in fine-tuning, prompt engineering, and responsible deployment with appropriate safeguards, monitoring, and auditability.
Proficiency in Python, TensorFlow, PyTorch, Spark, or Scala, coupled with experience in big data technologies such as Hadoop, AWS, and Hive, and familiarity with MLOps tooling that supports model monitoring, drift detection, and end-to-end auditability.

Preferred Qualifications

Strong expertise, interest, and track record of performing cutting-edge research on Gen-AI
Proven track record in designing, building, and deploying high-quality machine learning models in production environments, demonstrating a strong ability to translate theoretical concepts into practical applications.
Demonstrated expertise in data wrangling and model building on a distributed Cloud computation environment (with stability, scalability and efficiency). GPU experience is desired.
Strong ownership and execution; proven experience in implementing models in production.