Quant Modeling [multiple Positions Available]

JPMorgan Chase JPMorgan Chase · Banking · Columbus, OH +1 · Corporate Sector

Quant Modeling role at JPMorgan Chase focused on designing, developing, and building tools for model prototyping, experimentation, evaluation, and deployment. The role involves working with data, building analytical applications on cloud platforms, and supporting modelers with technology and infrastructure needs. It requires extensive experience in data processing, data science tools, automation, and credit risk modeling within the consumer lending lifecycle.

What you'd actually do

  1. Design, develop, and build tools to support prototyping, experimenting, evaluating, and deploying models.
  2. Work with modelers and analysts to collect feedback on modeling tools for product designs.
  3. Work with platform teams to leverage existing platforms to build modeling tools and provide improvement feedback.
  4. Evaluate and select open source or proprietary tools required to meet data and modeling requirements.
  5. Answer key business questions by leveraging existing data assets or creating new ones.

Skills

Required

  • Designing and developing source code for analytical application using automated and distributed data processing systems on UNIX and Hadoop platforms
  • Data acquisition, transformation, feature engineering, exploratory analysis, visualization, and data storage using data science and analytics tools including SQL, Spark, Python, R, and SAS
  • Automations using UNIX or LINUX shell scripts integrating Python, Distributed framework Spark, RDBMS such as Teradata, Oracle, or any Cloud database such as Snowflake
  • Storing and versioning source code using version control tools and processes such as Bitbucket or Git
  • Origination, sale and servicing, default management and loss mitigation, credit risk modeling, and loss forecasting methodology with Consumer Lending including Auto Finance, Home Lending, Card, and Business Banking lending lifecycle
  • Designing and Developing distributed Analytical application on AWS Cloud using Amazon S3, Apache Spark, and Amazon EMR

What the JD emphasized

  • Design, develop, and build tools to support prototyping, experimenting, evaluating, and deploying models
  • Data acquisition, transformation, feature engineering, exploratory analysis, visualization, and data storage
  • Automations using UNIX or LINUX shell scripts integrating Python, Distributed framework Spark, RDBMS
  • Origination, sale and servicing, default management and loss mitigation, credit risk modeling, and loss forecasting methodology with Consumer Lending