As a Staff ML Risk Analyst on the Growth & Risk team within the Consumer & Business group, you'll sit at the intersection of fraud intelligence and machine learning infrastructure, defining how we identify, model, and respond to sophisticated fraud at scale. Fraud at Coinbase is fast-evolving, with professional, adaptive counterparties that outpace any human response team. You'll build and shape the ML-powered, automated solutions that detect and prevent account takeover (ATO) and scam activity before it reaches our users, setting the technical direction for the ML Analytics function within Growth & Risk.

What you'll do:

• Define the ML data and feature strategy for fraud detection, determining what data needs to enter our systems so models can take intelligent, high-accuracy action on the small fraction of traffic where intervention matters most.
• Own the end-to-end feature engineering pipeline, identifying, building, validating, and promoting features that drive measurable improvements in ATO and scam ML performance.
• Diagnose gaps between current tooling infrastructure and the solutions needed, driving the roadmap to close them by applying deep knowledge of how the ML industry has evolved architecturally.
• Partner with Machine Learning Engineers to translate analytical insights into production-ready ML systems, ensuring models are instrumented, monitored, and continuously improved.
• Mentor junior team members across the ML Analytics function, defining the technical approach and translating direction into execution.
• Partner cross-functionally with Product Managers and Risk Analysts to surface fraud signals and translate ML findings into business-impacting decisions.

Required Skills and Experience:

• 8+ years of hands-on experience in machine learning analytics, data science, or a related technical field, with meaningful experience applied to risk, fraud, or payments problems.
• Practitioner-level proficiency in Spark, Python, and big data ML as a core working stack, with demonstrated ability to operate beyond SQL and rule-based approaches.
• Proven experience in feature engineering for ML models, including identifying signals, building pipelines, and validating feature quality at scale.
• Working knowledge of the ML infrastructure landscape evolution, from Hadoop-era big data through modern feature stores (e.g., Tecton, Feast), with the ability to apply that context to close infrastructure gaps.
• Demonstrated ability to optimize ML systems for sensitivity and accuracy on high-stakes, low-volume fraud traffic rather than broad-coverage, high-volume use cases.
• Utilizes generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality.