Senior Data Scientist (Credit Risk)

Braviant Holdings•Dallas, TX

3d•Hybrid

About The Position

Braviant is a leading provider of tech-enabled credit products that combines breakthrough technology and cutting-edge machine learning to transform how people access credit online. Our next-generation approach to lending reduces credit barriers and creates a Path to Prime to help millions of underbanked consumers build credit history, reduce their cost of borrowing, and take control of their personal finances. Braviant has been named multiple times to the Inc. 5000 list of fastest growing private companies and has been recognized as a Best Place to Work by Crain’s Chicago, BuiltIn Chicago and American Banker. We are building and scaling a high-performance consumer lending platform and are looking for a Senior Data Scientist to drive credit decisioning across the loan lifecycle. This role sits at the intersection of credit strategy, fraud, and analytics, directly impacting approval strategy, loss performance, and portfolio profitability. You will build and deploy models that inform key decisions around who we approve, how we price risk, and how we manage portfolio performance. This is a hands-on, high-impact role suited for someone who is business-oriented, data-driven, and biased toward action, not just model development. You will partner closely with Credit, Fraud, Servicing, Product, and Engineering to translate data into clear, actionable decisions that improve approval quality, reduce early loss, and drive sustainable growth.

Requirements

Degree in Data Science, Applied Mathematics, Statistics, Economics, Computer Science or a related field
5-7 years of professional experience in Data Science, Analytics or a related field within FinTech or online lending space.
Advanced proficiency in Python for programming, data analysis, and predictive modeling
Proficiency in SQL, Excel and experience with data visualization tools
Excellent knowledge in applied statistical methods and experience using various predictive machine learning techniques including: linear models, decision trees, boosting, and ensemble models
Knowledge of optimization, stochastic processes, experimental design, A/B testing and bootstrapping
Passion for keeping your skills up to date and exploring new methodologies
The ability to distill complex problems and analysis into a clear and concise narrative

Nice To Haves

Experience in subprime consumer lending, fintech, payments, or another regulated financial services technology environment.
Hands-on experience applying AI to credit risk management

Responsibilities

Develop and deploy predictive models across the credit lifecycle (acquisition, risk, and collections) with a focus on improving approval quality and loss performance.
Translate model outputs and analysis into actionable credit strategy, including approval cutoffs, segmentation, and decision rules.
Analyze portfolio performance (FPD, delinquency, loss) to identify key drivers of deterioration and recommend targeted actions.
Evaluate tradeoffs between approval rate, loss, and profitability, and recommend strategies to optimize portfolio performance.
Distinguish fraud risk vs credit risk, improving early default performance and reducing losses.
Design and execute experiments (A/B tests, champion/challenger frameworks) to evaluate strategies and drive continuous improvement.
Work with Product and Engineering to implement decisioning logic into production systems and ensure accurate execution.
Monitor model and strategy performance over time, identifying drift, instability, or unintended impacts on portfolio outcomes.
Collaborate cross-functionally with other departments to ensure decisions align with business goals and risk appetite.