Senior Manager, Fraud Strategy & Operations

Raisin•Sandy, UT

2d•Hybrid

About The Position

The Fraud and Risk Operations team safeguards Raisin’s U.S. business by monitoring, detecting, and mitigating risks across the customer lifecycle. We manage fraud prevention, investigations, payments risk, fraud recovery, and while supporting 2nd line AML/KYC oversight. It partners closely with Product, Engineering, Compliance, and Customer Service to ensure safe and frictionless customer experiences. As a multi-bank deposit marketplace targeting rapid growth, Raisin faces complex, evolving multi-vector fraud challenges across onboarding, identity verification, bank linking, and money movement. Fraud and Risk Operations is at the center of designing the strategies, controls, and analytical foundations that protect the platform at scale.

Requirements

8+ years in fraud risk management, fraud analytics, fraud data science, AML/financial crime, or payments risk (fintech, digital banking, payments a strong plus).
Strong technical skills: Python, SQL, and experience with feature engineering, model development, and fraud analytics.
Proven ability to design, deploy, and monitor machine learning models in production.
Deep familiarity with U.S. fraud typologies: identity fraud, mule activity, ATO, synthetic IDs, ACH fraud, bank linking fraud, and payment abuse.
Understanding of AML/KYC frameworks and how they intersect with fraud controls.
Experience influencing decisions across Product, Engineering, Compliance, and Operations.
Excellent communication skills with the ability to present insights to executive leadership.
Strategic, analytical mindset with a focus on balancing fraud prevention, operations scalability, and customer experience.
Leadership experience, formal or informal, and ability to scale influence across teams.

Responsibilities

Design, test, and deploy real-time logic within the risk rules engine (e.g., velocity checks, device fingerprinting triggers, IP risk thresholds, and behavioral anomalies, etc.) to intercept fraudulent actions during the entire customer lifecycle.
Partner with internal and external platform partners to integrate, build and implement both customer and transaction level fraud scores into the rules engine, creating conditional logic that automatically approves, blocks, or challenges high-risk events.
Monitor and optimize false positive rates to ensure legitimate customer transactions pass through with minimal friction.
Build detective monitoring rules, threshold alerts, and transaction reports to identify complex fraud patterns, first party fraud triggers, account takeover, synthetic ID, or coordinated fraud rings after events occur.
Conduct post-mortems on confirmed fraud instances and Reg E disputes to identify gaps in existing rule sets and rapidly deploy backtest-verified countermeasures.
Regularly review, backtest, and refine active rules to eliminate stale logic, reduce redundancy, and adapt to shifting fraud tactics. Utilize the iterations of rules to also actively monitor the existing customer book.
Active work internally and externally to seek additional risk signals, and proactively deploy to stay ahead of emerging fraud patterns.
Responsible for partnering with the Head of Fraud to own and execute Raisin’s U.S. fraud strategy across onboarding, account linking, and payment flows.
Design and refine fraud policies, rules, controls, and escalation processes.
Lead fraud investigations end-to-end and translate findings into durable controls.
Build fraud KPIs, dashboards, and performance reporting for leadership.
Quantify fraud exposure, loss trends, and efficiency metrics to inform strategic decisions.
Own the roadmap for fraud models across the customer lifecycle.
Build and maintain customer risk profiling and scoring frameworks and enhance monitoring of high-risk customers.
Design, implement, and deploy machine learning models for anomaly detection, identity risk, behavioral analytics, and transaction monitoring.
Build features from device, behavioral, graph, identity, ACH/payment telemetry, and network data.
Partner with Engineering and Data to ensure high-quality data pipelines for real-time model scoring.
Translate model outputs into practical decision strategies (rules, thresholds, step-up flows).