Data Scientist

PatientFi

1d

About The Position

As a Data Scientist at PatientFi, you will play a key role in developing industry-leading machine learning models for managing credit and fraud risks. You will work with multiple complex data sources, such as credit bureau reports and customer-supplied information, to optimize underwriting decisions, approve/decline strategies, credit line assignments, and fraud detection methodologies.

Requirements

• 1+ years of experience in Data Science, Credit Risk, Fraud Risk, Quantitative Analytics, or related fields
• Advanced degree (M.S./PhD preferred) in Statistics, Computer Science, Engineering, Economics, or a related quantitative field
• 1+ years of relevant experience within consumer credit risk management, ideally at a FinTech startup, banking or lending company; bonus points for healthcare experience
• Expertise in Python and SQL, with a strong understanding of coding best practices and model documentation
• Experience implementing data pipelines using Google Cloud products (BigQuery, GCS, Cloud DataFlow, Cloud Pub/Sub, Cloud BigTable)
• Understanding of data warehousing concepts, data engineering, and data modeling
• Strong experience in risk modeling, fraud detection, and machine learning techniques applied to financial services.
• Strong communication and interpersonal skills, with the ability to clearly translate technical insights to business stakeholders
• Self-motivated, results-oriented, and capable of managing multiple projects in a fast-paced environment
• Experience working with Looker (or similar BI tools like Tableau, Power BI) to design reports/dashboards
• Familiarity with bureau data and alternative data sources for credit and fraud risk analysis

Nice To Haves

• Knowledge of cash flow modeling and loss forecasting is a plus

Responsibilities

• Develop and implement machine learning models for credit risk assessment and fraud detection, ensuring compliance with lending best practices and regulatory requirements
• Build and improve quantitative and qualitative models (including CECL, Prepayment, Weighted Average Remaining Maturity (WARM), Probability of Default and Loss Given Default (PD/LGD) methodologies)
• Leverage advanced data analytics to dynamically segment applicants and loans based on behavior and performance
• Optimize risk-based pricing strategies, underwriting criteria, and collections strategies using data-driven insights
• Collaborate with engineers to deploy machine learning models into production environments
• Monitor, analyze, and report on model performance, ensuring continual refinement and adaptation to changing market conditions
• Develop LookML and SQL queries to build dashboards in Looker for tracking model and business performance
• Extract the most value from data to drive key business metrics and enhance risk management strategies
• Conduct ad-hoc analysis to support risk management, investor services, operations, and corporate development
• Support analysis and reporting in stress testing models

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Number of Employees: 51-100 employees