Fraud Data Scientist
Coinflow provides global payment acceptance, instant blockchain settlement, and real-time payouts for online businesses.
Funding history
About Coinflow
Coinflow is a payments company that connects traditional payment methods such as cards and bank transfers with stablecoin settlement on public blockchains. Its APIs and low-code widgets let merchants accept payments, settle funds instantly in USDC, issue real-time payouts, and manage chargeback protection and marketplace split payments across more than 130 countries.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will analyze fraud models and rules across payment rails and merchant segments. You will identify emerging fraud patterns, explore and validate new signals, manage label-quality feedback loops, design experiments, evaluate vendors, tune risk strategies, and produce clear performance reporting for stakeholders.
Requirements
- 4+ years of data science or analyst experience in fraud, risk, or abuse
- Strong SQL and Python skills
- Knowledge of fraud-model statistics and machine-learning concepts
- Understanding of card-not-present fraud, account takeover, card testing, friendly fraud, and chargebacks
- Experience evaluating messy, imbalanced, delayed-label data
- Experience designing and analyzing experiments
- Ability to explain model behavior and tradeoffs to stakeholders
- Experience with graph or network analysis is a plus
- Experience with AI-native tooling or willingness to use it
Responsibilities
- Analyze fraud model and rule performance by merchant segment
- Identify emerging fraud patterns and quantify their impact
- Explore transaction, device, behavioral, identity, and network signals
- Prototype and validate model features
- Manage ground-truth labels and feedback loops
- Design and analyze backtests, shadow tests, and champion-challenger experiments
- Evaluate third-party fraud vendors
- Recommend rules, thresholds, authentication, and decision strategies
- Create explainable reporting on model decisions and performance
Benefits
- Equity
