AI Credit Default Risk Modeler

Gradrix Works

Remote · $130k – $160k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Our clients include 18 regional banks and 7 credit unions who have been underwriting consumer and SMB loans with the same FICO-centric models for fifteen years. Regulatory pressure and competitive dynamics from fintech lenders are forcing a rethink. FICO alone leaves money on the table: creditworthy borrowers get rejected, and high-risk borrowers with good scores still default. We build the alternative credit risk models that fix this. You'll own the credit default prediction stack for our SMB lending clients: designing models that incorporate bank statement cash flow signals, payment behavior across utility and telecom providers, and business network relationships alongside traditional bureau data. The constraint is explainability — regulators require that adverse action decisions be described in terms a loan officer can explain to a borrower. SHAP values and model cards are part of the output, not an afterthought. This is a senior IC role with client-facing responsibility. You'll present model validation results to bank risk committees and respond to examiner questions. Technical depth and regulatory fluency are equally important.

Fully remote.

Responsibilities

Design credit default prediction models incorporating alternative data sources beyond bureau scores
Build cash flow feature engineering from bank statement transaction data
Implement explainability outputs satisfying adverse action notice requirements
Validate models against OCC and FDIC model risk management guidelines
Conduct fair lending analysis and document disparate impact testing
Present model performance to client credit committees and regulatory examiners

Requirements

6+ years in credit risk modeling or financial ML with regulatory experience
Deep understanding of ECOA, FCRA, and model risk management frameworks
Strong Python, SQL, and statistical modeling skills
Experience with SHAP, LIME, or other explainability techniques for regulatory use
Comfort presenting technical findings to non-technical banking executives