Data Scientist - Credit (Retros)

Responsibilities

• Deep-dive into model performance for clients, triage issues, and identify opportunities to improve outcomes
• Analyze Plaid’s unique data to identify emerging credit risk signals and build and evaluate credit retrospectives
• Create tailored recommendations for clients based on their data and Plaid’s insights
• Build and maintain data pipelines, including ETL processes using tools such as dbt
• Develop metrics, alerts, and dashboards to monitor production machine learning model performance
• Own the process of developing hands-on recommendations for incorporating cash flow insights into lending decisions, using best practices for account-level decisioning
• Improve customer adoption of Plaid Insights through custom analysis tailored to each customer’s needs
• Serve as a subject matter expert on credit insights and credit policy implementation, supporting Data Science, Engineering, and Go-to-Market partners
• Apply your expertise in quantitative analysis, data mining, and data visualization to develop models and actionable insights
• Identify useful signals that can inform machine learning models
• Inform and influence Product and Engineering teams through clear analysis and presentations

Preferred

• Experience building data pipelines and automating ETL processes with dbt or similar tools

Benefits

• Equity and/or commission, dependent on the position offered.
• Medical, dental, and vision coverage.
• 401(k).
• Hybrid work arrangement.
• Glassdoor
• 4.3
• Financial data network connecting bank accounts to fintech apps.
• San Francisco, California, USA
• https://plaid.com
• Distribution of Different Job Fields Receiving Sponsorship
• Represents job field similar to this job
• Engineering and Development
• Product Management
• Management and Executive
• Accounting and Finance
• Legal and Compliance
• Creatives and Design
• Customer Service and Support
• Sales
• Marketing
• Trends of Total Sponsorships
• *2026
• (26)
• 2025
• (41)
• 2024
• 2023
• (42)
• 2022

Qualifications

• 2–5 years of industry experience in a financial services Data Science role
• Deep familiarity with SQL and Python
• Deep understanding of credit risk and the development of underwriting models
• Hands-on credit expertise building and maintaining credit policies for lenders
• Knowledge of the lending lifecycle and how to optimize each step, including marketing, acquisition, customer management, and collections or recoveries
• Demonstrated ability to make data-driven decisions
• Experience building data pipelines and automating ETL processes with dbt or similar tools
• 2–5 years of industry experience in a financial services Data Science role.

Required skills

• Credit Policy, Credit Risk, Dbt, ETL, Financial Services Data Science, Lending Lifecycle, Python, SQL, Underwriting Models

Experience

• 2-5 years