Data Scientist, Fraud

Details

Who We Are

About Stripe

Stripe is a financial infrastructure platform for businesses. Millions of companies—from the world's largest enterprises to the most ambitious startups—use Stripe to accept payments, grow their revenue, and accelerate new business opportunities. Stripe's mission is to increase the GDP of the internet.

About the Team

The Data Science team partners with teams across Stripe to provide the models, data products, and insights needed to make decisions and grow responsibly. The Fraud, Losses, and Financial Crime Data Science team builds models and data products that protect Stripe and its users from fraud, account takeover, and financial crime.

The team owns the full fraud and loss modeling stack, including account takeover detection, card fraud classification, merchant-level loss estimation, unsupervised anomaly detection, and financial crime risk modeling. The team partners with Fraud Engineering, Financial Crimes Engineering, and Risk Operations to bring these systems into production and measure their impact on Stripe's financial integrity and user trust.

Responsibilities

• Build and improve the models powering Stripe's fraud detection and loss management systems.
• Work closely with Fraud Engineering and Risk Operations to move models from research into production.
• Use data to surface insights that shape fraud strategy across the business.
• Apply supervised and unsupervised machine learning, statistical modeling, causal inference, optimization, and experimentation to risk problems in global payments.

Requirements

Minimum Requirements

• PhD with 1–3 years, MS or MA with 2–6 years, or BS or BA with 4–8 years of data science or quantitative modeling experience.
• Experience with fraud, risk, or financial crimes.
• Proficiency in SQL and a computing language such as Python or R.
• Experience working with cross-functional teams to deliver results.
• Ability to communicate results clearly and a focus on driving impact.
• Demonstrated ability to manage and deliver multiple projects with strong attention to detail.
• Strong business acumen and experience synthesizing complex analyses into actionable recommendations.
• Proficiency with AI tools to accelerate model development, analysis, and coding.

Preferred Qualifications

• Strong knowledge and hands-on experience in several of the following areas: machine learning, statistics, optimization, causal inference, and experimentation.
• Experience deploying models in production and adjusting model thresholds to improve performance.
• Experience designing, running, and analyzing complex experiments or using causal inference designs.
• A builder's mindset and willingness to question assumptions and conventional wisdom.
• Experience with distributed tools such as Spark and Hadoop.
• A PhD or MS in a quantitative field, such as Statistics, Engineering, Mathematics, Economics, Quantitative Finance, Sciences, or Operations Research.