Senior Fraud Data Scientist | Payments & Fintech

Ant-Tech•Chicago, IL
•$120,000 - $180,000

About The Position

The Senior Fraud Data Scientist will analyze and improve fraud models, detection rules, and risk strategies across payment systems. The role involves identifying emerging fraud patterns, exploring transaction and related data for predictive features, and designing model evaluations and experiments. The position balances fraud prevention with payment approval rates and improves data quality through feedback from chargebacks, disputes, and manual reviews. The scientist will communicate findings and recommendations to engineering, risk operations, compliance, and leadership. The role offers ownership of fraud prevention strategies at a rapidly scaling fintech company, with work spanning global payment networks and the intersection of AI, stablecoins, and next-generation payment infrastructure.

Requirements

  • 4+ years of experience in Data Science or Analytics, specializing in fraud, risk, or abuse detection.
  • Background in payments, fintech, financial services, or online marketplaces.
  • Proven experience improving production fraud models or risk rules with measurable business impact.
  • Strong proficiency in SQL and Python.
  • Solid understanding of machine learning and statistical concepts, including gradient-boosted trees, model calibration, and imbalanced datasets.
  • Deep knowledge of payment fraud patterns, including card-not-present fraud, account takeover, card testing, friendly fraud, and chargebacks.
  • Experience with experimentation, model evaluation, and fraud strategy optimization.
  • Strong analytical thinking and the ability to communicate technical insights to non-technical stakeholders.

Nice To Haves

  • Familiarity with graph analytics, network analysis, or fraud ring detection.
  • Experience with AI-native tools or enthusiasm for integrating AI into daily workflows.

Responsibilities

  • Analyze fraud model and rule performance, tracking approval rates, fraud losses, false positives, and model drift.
  • Identify emerging fraud patterns, including account takeover, card testing, fraud rings, friendly fraud, and bonus abuse.
  • Explore transaction, device, behavioral, identity, and network data to identify new predictive features.
  • Design and evaluate backtests, shadow tests, and champion/challenger experiments.
  • Optimize fraud detection strategies, thresholds, and rules to balance fraud prevention with payment approval rates.
  • Improve data quality and feedback loops using chargebacks, disputes, and manual review outcomes.
  • Translate complex analytical findings into actionable recommendations for engineering, risk operations, compliance, and leadership.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service