Data Scientist - Fraud
We are the Data team within Plaid’s Fraud organization. We build the machine learning systems that power Plaid’s fraud detection products, leveraging Plaid’s network data to help identify and prevent fraud before it happens. Our team owns the end-to-end ML lifecycle, from feature pipelines and model training to production serving and monitoring, ensuring our systems are reliable, scalable, and built to support hundreds of customers and data partners.
As a Data Scientist on the Fraud Data team, you will analyze customer and network traffic to understand how Plaid Protect performs across a range of use cases and customer segments. You’ll build dashboards and metrics that provide a clear, shared view of product performance, run backtests to evaluate performance and identify high-impact rules and model strategies, and generate insights that support customer growth and expansion. You’ll also design scalable data models and schemas to enable reliable analysis and reporting, while partnering closely with Product and Engineering to design and analyze experiments for new customer-facing features.
Responsibilities:
- Work at the intersection of product analytics, machine learning, and fraud and risk to uncover insights that improve product performance.
- Own the metrics, dashboards, and experiments that inform product strategy and decision-making.
Qualifications:
- 3–5 years of relevant experience, including at least 2–3 years working extensively with product analytics, experimentation, or data-driven products.
- Strong proficiency in SQL and Python, with experience analyzing complex datasets and translating insights into action.
- Hands-on experience with product analytics, experimentation, and/or backtesting methodologies.
- Experience building and maintaining dashboards, reporting frameworks, and core product metrics.
- Strong communication and stakeholder management skills, with the ability to translate complex analyses into clear, actionable insights for technical and non-technical audiences.
Nice-to-Have:
- Experience in fraud/risk domains
- Experience with developing ML models