Principal Data Scientist, Fraud Modelling

About the Company

impact.com is the world’s leading commerce partnership marketing platform, transforming the way businesses grow by enabling them to discover, manage, and scale partnerships across the entire customer journey. Over 5,000 global brands, including Walmart, Uber, and Shopify, rely on impact.com to power their partnerships.

Responsibilities

• Conduct R&D on fraud detection and risk monitoring across the digital advertising ecosystem
• Design, prototype, and validate ML models and rule-based systems for fraud detection and partner risk scoring
• Research and apply graph-based fraud detection techniques to uncover coordinated fraud rings
• Deploy Fraud and Risk ML models to production, owning end-to-end delivery from ETL to monitoring
• Iterate on live models to improve precision, recall, and F1 scores while reducing false positives
• Perform deep-dive analyses on fraud trends to inform model strategy and business decisions
• Partner with Product, Engineering, Compliance, and Finance to align on success metrics

Requirements

• 5+ years in data science, ML, or advanced analytics
• 2+ years focused on fraud detection, risk modeling, or anomaly detection in production
• Strong proficiency in Python and SQL
• Experience with ML libraries such as scikit-learn, XGBoost, or LightGBM
• Expertise in feature engineering and handling imbalanced datasets
• Bachelor's degree in a quantitative field (CS, Statistics, Math, or Engineering); Master's or PhD preferred

Preferred Qualifications

• Experience in affiliate marketing, ad tech, or e-commerce fraud
• Familiarity with browser extension detection or device fingerprinting
• Experience with graph analytics or network-based fraud detection
• Knowledge of GCP tools (BigQuery, Vertex AI) or Databricks/Spark
• Experience with real-time scoring and low-latency deployment

Benefits

• Flexible working with a Responsible PTO policy
• Mental health support including 12 covered therapy sessions per year
• Monthly gym reimbursement
• Restricted Stock Units (RSUs) with a 3-year vesting schedule
• Free Coursera subscription and PXA courses
• Generous parental leave (26 weeks primary, 13 weeks secondary)
• Technology stipend and monthly internet allowance