Data Analyst - Fraud Intelligence
Join Sardine's Fraud Intelligence team to evaluate vendor data signals and partnerships, build testing frameworks, define fraud-outcome evaluation criteria, translate findings into recommendations, support data engineering ingestion requirements, document vendor performance, and investigate fraud trends, model performance, and client-specific data questions.
Responsibilities
- Design and execute structured evaluation frameworks for vendor data assets.
- Build lift analyses, backtests, and champion/challenger comparisons.
- Profile vendor datasets for completeness, freshness, match rates, and population coverage.
- Define evaluation criteria tied to fraud outcomes with fraud leadership.
- Translate vendor data findings into actionable recommendations.
- Partner with data engineering on ingestion requirements and production-like test environments.
- Document evaluation results and maintain an internal knowledge base.
- Support deep dives into fraud trends, model performance, and client-specific data questions.
Requirements
- 3–5 years of experience in data analysis, data science, or a related analytical role.
- Proficiency in SQL and Python or R for data manipulation, statistical analysis, and visualization.
- Understanding of precision, recall, AUC, ROC, lift, population distributions, and A/B testing.
- Experience evaluating external or third-party datasets, including data quality, match rates, and signal value.
- Strong written and verbal communication skills.
- Comfort with ambiguity and defining structure in a fast-moving environment.
Benefits
- Generous cash and equity compensation
- Early exercise for all options, including pre-vested options
- Flexible paid time off and year-end break
- Health, dental, and vision coverage for employees and dependents in the US and Canada
- 4% 401k or RRSP matching in the US and Canada
- MacBook Pro
- Home office setup stipend
- Monthly meal stipend
- Monthly social meet-up stipend
- Annual health and wellness stipend
- Annual learning stipend