Junior Data Scientist at Piper Companies
Tysons Corner, Virginia, USA -
Full Time


Start Date

Immediate

Expiry Date

06 Sep, 25

Salary

90000.0

Posted On

06 Jun, 25

Experience

3 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

No

Skills

Models, Data Manipulation, Predictive Modeling, Underwriting, Model Development, Business Insights

Industry

Financial Services

Description

Piper Companies is seeking a Junior Data Scientist, to join one of the largest federal credit unions. The Junior Data Scientist will support risk modeling and credit policy development across various consumer banking products.

QUALIFICATIONS FOR THE JUNIOR DATA SCIENTIST INCLUDE:

  • 3+ years of experience in the banking, credit union, FinTech, or insurance industries, with hands-on involvement in modeling for credit policy and risk mitigation.
  • Strong technical skills in data manipulation, analysis, and model development using these core tools.
  • Experience with predictive modeling, feature engineering, and statistical techniques, particularly in underwriting or customer management for credit products.
  • Ability to clean, merge, and analyze high-volume, multi-source data to support model development and business insights.
  • Capable of presenting data-driven insights to stakeholders and working cross-functionally to implement models and align with business goal
Responsibilities
  • Build machine learning models to support credit policy, risk mitigation, and marketing strategies across consumer banking products like credit cards, auto loans, and personal loans.
  • Clean, merge, and transform large datasets from multiple sources, and engineer features to optimize model performance and accuracy.
  • Analyze data to uncover trends, detect anomalies, and generate insights that inform model development and business decisions.
  • Present findings and model insights to senior stakeholders and work closely with business and technical teams to ensure successful model implementation.
  • Use statistical methods and machine learning algorithms (e.g., XGBoost, GLM) to enhance model robustness, address data imbalances, and validate credit risk and fraud models.
Loading...