Senior Quantitative Engineer - Single Family Loan Performance

people who care so that you can deliver on the following responsibilities:

• Communicate with model development team to understand and finalize requirements in the form of model whitepapers and/or research code.

• Translate moderately complex mathematical, business, and financial modeling logic into software code, as well as design and execute modeling application systems via distributed computing both on premise and on external cloud to achieve efficiency, scalability, and modularity.

• Assist in solution design and implementation of SF mortgage loan performance (Borrower Behavioral and Severity) models for production. Perform development testing including Unit-Test and reconciliation testing with research code.

• Apply statistical and machine learning techniques using Python, SQL, and AWS tools to enhance loan performance analytics.

• Assist in designing and testing model components for use in production systems, ensuring accuracy, scalability, and compliance.

• Collaborate with modelers, data scientists, and business stakeholders to translate insights into strategies that drive loss mitigation and servicing efficiency.

• Contribute to technical documentation, model governance requirements, and model risk audits.

• Work within Agile teams to iterate and deliver high-impact modeling solutions on time and at scale.

• Research and evaluate emerging technologies and industry best practices of model and analytical system implementation.

THE EXPERIENCE YOU BRING TO THE TEAM

Minimum Required Experiences:

• 2+ years of experience in quantitative modeling, data science, or financial analytics, preferably in mortgage servicing, loss mitigation, or credit risk

• Proficiency in Python and data science packages (NumPy, Pandas, Scikit-learn, XGBoost, etc

• Skilled in SQL, Linux shell scripting, and working knowledge of AWS cloud infrastructure

• Understanding of loan performance analytics, including delinquency modeling, loan modification outcomes, and loss severity

• Experience developing and deploying models within a full software development life cycle (SDLC), using object-oriented programming and Git

• Technical writing and communication skills for model documentation, regulatory review, and stakeholder engagement

• Familiarity with model governance, audit processes, and regulatory compliance expectations

• Bachelor's degree in a quantitative field (e.g., Statistics, Applied Math, Computer Science, Information Technology, Engineering) or related field

Desired Experiences:

• Masters or PHD degree in a quantitative field (e.g., Statistics, Applied Math, Computer Science, Information Technology, Engineering)

• Experience with Generative AI or advanced ML applications in loan performance or borrower behavior modeling

• Prior work in a GSE, financial institution, or mortgage servicing environment.

• Understanding of loss mitigation programs, forbearance, and default servicing policies

Qualifications

Education:
Bachelor's Level Degree (Required)

The future is what you make it to be. Discover compelling opportunities at Fanniemae.com/careers.

Fannie Mae is a flexible hybrid company. We embrace flexibility for our employees to work where they choose, while also providing office space for in-person work if desired. At times, while business need may call for on-site collaboration, which means proximity within a reasonable commute to your designated office location is preferred unless job is noted as open to remote.

Fannie Mae is an Equal Opportunity Employer, which means we are committed to fostering a diverse and inclusive workplace. All qualified applicants will receive consideration for employment without regard to race, religion, national origin, gender, gender identity, sexual orientation, personal appearance, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation in the application process, email us at [email protected]

Requisition compensation:
121000
to
158000