Manager, Fraud

Purpose Financial•Greenville, SC

2d•Onsite

About The Position

The Manager, Fraud leads Purpose Financial’s fraud risk analytics and strategy across the customer lifecycle, including application and origination, identity verification, funding, payments, and account servicing across store and online channels. The role detects, prevents, and measures third-party and synthetic identity fraud, first-party fraud and bust-out, payment fraud, and account takeover while balancing loss reduction with approval rates, customer experience, and operational cost. It is a hands-on player-coach position that combines data analysis, modeling, and strategy design with leading and developing a team of fraud analysts and data scientists. The role partners closely with Credit Risk to classify losses accurately and align fraud controls with credit policy. Depending on experience, the position may be filled at Manager or Senior Manager level; Senior Manager scope includes broader roadmap ownership, a larger team, and greater executive-facing accountability. The position reports to the Director, Data Science and Credit Risk. It is based at the company’s downtown Greenville office, which offers free parking, an onsite gym, and free snacks and drinks. Travel is 0–10%, and attire is business casual.

Requirements

Bachelor’s degree in a quantitative field such as Engineering, Statistics, Mathematics, Economics, Computer Science, or a comparable field.
Manager: At least 5 years of experience in fraud analytics, fraud strategy, or risk data science, preferably in consumer lending, fintech, or payments, including at least 2 years leading or mentoring analysts or data scientists.
Senior Manager: At least 8 years of experience in fraud analytics, fraud strategy, or risk data science, including at least 4 years of people management and demonstrated ownership of fraud strategy or enterprise-level fraud loss outcomes.
Advanced proficiency in SQL and Python or R for data manipulation, analysis, and modeling.
Hands-on experience building, deploying, and monitoring fraud models using machine-learning techniques, including gradient boosting, anomaly detection, or graph/network analysis, and handling class imbalance and delayed or noisy fraud labels.
Direct experience with data quality, ELT, and feature engineering for fraud identification, including identity, device, velocity, and payment-behavior features.
Deep knowledge of consumer lending fraud typologies and controls, including synthetic and stolen identity, first-party fraud and bust-out, account takeover, payment fraud, and ACH fraud.
Experience with fraud and identity data vendors, consortium data, and decision engines or rules platforms.
Solid understanding of experimental design and statistical principles, including hypothesis testing, p-values, statistical power, and causal inference.
Working knowledge of model risk management and consumer lending regulatory expectations, including FCRA, ECOA/Regulation B, adverse action, fair lending, data privacy, and information security.
Understanding of the interaction between fraud and credit risk, including loss classification and its effects on credit models, pricing, and loss forecasting.
Proven ability to hire, develop, and manage a high-performing team.
Excellent written and verbal communication skills, including the ability to explain complex analysis and make clear recommendations to non-technical audiences.
Ability to work independently, manage multiple projects in a dynamic, high-volume, fast-paced environment, and adapt to change.
Ability to understand and ensure compliance with policies, procedures, and laws governing the industry, business, and products.
Ability to interact professionally and maintain business relationships across the organization and with external partners.
Must be eligible to work in the USA and able to pass a background check.

Nice To Haves

Master’s degree or PhD in a quantitative field.
Experience in subprime or near-prime consumer lending.
Experience with cloud data platforms and version control, such as Git.

Responsibilities

Develop, implement, and monitor fraud detection models, including statistical and machine-learning models, and rules across the customer lifecycle.
Design and manage fraud decision strategies, including rules, model cutoffs, step-up identity verification, and manual review queues, balancing fraud losses against approval rates, false positives, and customer friction.
Partner with Credit Risk to define and maintain fraud-versus-credit loss classification, including first-payment default, never-pay, and confirmed-fraud tagging.
Monitor fraud KPIs; build early-warning dashboards and alerting; and lead root-cause analyses of emerging attacks, fraud rings, and loss spikes.
Identify and respond to evolving threats, including synthetic identities, AI-generated or altered documents, deepfake and biometric spoofing, bot-driven application attacks, and payment and ACH return abuse.
Design and run champion/challenger experiments to measure and optimize fraud strategies, verification steps, line assignment, and offer terms across products, channels, and customer segments.
Evaluate, select, and manage third-party fraud data and tool vendors, including retro testing, ROI analysis, and ongoing performance monitoring.
Partner with Technology to implement models and rules in production decisioning systems, define data requirements, and ensure accurate, timely data pipelines and feature engineering.
Work with Fraud Operations, Store Operations, and Customer Service to translate analytics into investigation workflows, queue prioritization, and front-line controls, and use investigation outcomes to improve models.
Ensure fraud models and strategies meet Model Risk Management standards and applicable consumer lending regulations; support documentation, validation, fair lending review, and adverse action requirements; and coordinate with Compliance, Legal, and Internal Audit.
Develop and maintain fraud prevention policies and procedures with Compliance and Operations.
Hire, lead, coach, and develop fraud analysts and data scientists; set priorities, review technical work, and maintain standards for code quality, reproducibility, and documentation.
Prepare and present reporting on fraud trends, losses, and strategy performance to the Director, Data Science and Credit Risk, and senior leadership, translating technical findings into business recommendations.
Build relationships with industry peers, consortiums, and fraud networks to stay current on fraud trends and prevention techniques.
At the Senior Manager level, own the multi-year fraud strategy and roadmap, recommend fraud loss and risk appetite targets, lead a larger team, and represent the fraud function with executives, auditors, and examiners.
Perform ad-hoc analysis and other assigned duties.

Benefits

Competitive wages
Health and life benefits
Health Savings Account with employer seed contribution
401(k) savings plan with company match
Paid parental leave
Company-paid holidays
Paid time off, including volunteer time
Tuition reimbursement
Business casual environment
Rewards and recognition program
Employee Assistance Program
Downtown Greenville office with free parking, onsite gym, and free snacks and drinks