Logo
RiskSpan

Lead Mortgage Credit Modeler

RiskSpan, Arlington, Virginia, United States, 22201

Save Job

Overview We are seeking a

quantitative modeler

with deep expertise in mortgage credit risk to design and implement advanced statistical and econometric models. This role will focus on loan-level performance modeling (delinquency, prepayment, default, loss given default) and structured mortgage asset valuation. The ideal candidate will combine rigorous quantitative training with hands-on experience in coding, model development, and empirical research.

Core Responsibilities

Develop and enhance

loan-level mortgage credit risk models

(transition matrices, hazard models, competing risks, survival analysis).

Implement

econometric and machine learning approaches

for prepayment, default, and severity modeling.

Conduct

back-testing, out-of-sample validation, and sensitivity analysis

to assess model robustness.

Analyze

large-scale loan-level datasets

(e.g., GSE loan-level, CoreLogic, Intex, private-label RMBS).

Build and document models in

Python/R/C++ , ensuring reproducibility and version control.

Partner with structured finance and risk teams to

integrate models into pricing, stress testing, and risk management frameworks .

Research

macroeconomic drivers of mortgage performance

and their incorporation into stochastic scenario design.

Author

technical model documentation

and research notes for internal stakeholders, model risk management, and regulators.

Technical Qualifications Required

Master’s or Ph.D. in

Quantitative Finance, Statistics, Econometrics, Applied Mathematics, or related quantitative discipline .

7+ years

of direct experience in

mortgage credit risk modeling or structured finance analytics .

Advanced skills in

statistical modeling : survival analysis, proportional hazard models, logistic regression, generalized linear models, panel data econometrics.

Strong programming expertise in

Python

(pandas, NumPy, scikit-learn, statsmodels) or

R .

Proficiency in handling

big data

(SQL, Spark, Snowflake and cloud-based data environments).

Deep knowledge of

mortgage credit risk dynamics , housing market fundamentals, and securitization structures.

Preferred

Experience with

Hierarchical models, and Monte Carlo simulation .

Knowledge of

machine learning algorithms

(e.g., gradient boosting, random forests, neural nets) applied to credit modeling.

Familiarity with

stress testing frameworks

and regulatory model governance needs.

Background in

RMBS cash flow modeling and structured product analytics .

This role is highly technical and research-driven. Candidates should be comfortable working with complex datasets, formulating empirical hypotheses, and coding full modeling pipelines from data ingestion through validation and deployment.

About RiskSpan RiskSpan is a leading source of analytics, modeling, data, and risk management solutions for the Consumer and Institutional Finance industries. We help financial institutions and regulators solve complex problems involving market, credit, and operational risk. Our clients include top banks, asset managers, servicers, and government-sponsored enterprises.

#J-18808-Ljbffr