Senior Data Scientist - Fraud Detection

DataVisor is building fraud detection capabilities for complex, high-stakes environments, and the Fraud Detection team is seeking a senior data scientist to bridge production machine learning with hands-on investigations. In this role, you will design and operationalize fraud detection features and models while also reconstructing attacker behavior to inform detection improvements.

What you’ll do

• Own the end-to-end lifecycle of fraud detection features and models, covering ideation and data exploration through prototyping, productionizing, and ongoing monitoring.
• Design highly predictive features using complex, large-scale, multi-dimensional data, including user behavior, device intelligence, network graphs, and transaction records.
• Build models and analyses on massive, noisy, imbalanced datasets (billions of events) using tools such as Spark, SQL, and the company’s proprietary AI platform.
• Use agentic AI to automate analytic pipelines and develop reusable skill tools that speed up fraud investigation, feature generation, and reporting workflows.
• Lead investigations into complex fraud across identities, accounts, devices, and transaction surfaces by reconstructing attacker sequences and forming hypotheses about actor intent and tooling.
• Write clear, evidence-backed technical reports and case studies for product, engineering, operations, legal, and executive stakeholders.
• Create fraud trend reports for customers by combining case-level findings with aggregate data into narratives customers can act on.

Requirements

• Master’s or PhD in Computer Science, Statistics, Mathematics, or a related quantitative field.
• 3+ years of applied experience in fraud detection, cybersecurity, or a related adversarial/high-velocity risk domain (fintech, consumer payments, banking, SaaS, marketplace risk, or security research).
• Strong knowledge of classic machine learning models such as Logistic Regression and Gradient Boosting.
• Hands-on experience deploying and iterating on machine learning lifecycles in a production environment.
• An investigator mindset, including pattern synthesis, hypothesis testing, and the ability to triage signal from noise in ambiguous, adversarial cases.
• Python programming skills (required) and SQL proficiency; PySpark experience is a plus.
• Experience working with large-scale data tools (such as Spark and Hadoop) and cloud platforms including AWS, GCP, or Azure.
• Excellent communication skills for explaining complex and technical behavior to both technical and non-technical audiences, including customers and executives.
• Professional proficiency in written and spoken English, with the ability to collaborate effectively in a global, cross-functional team.

Tools and technologies

• Python, SQL, PySpark, Spark, Hadoop
• AWS, GCP, Azure
• Logistic Regression, Gradient Boosting, agentic AI

Location and compensation

• Location: Mountain View, CA (onsite)
• Salary: USD 140,000 to 170,000 per year

Benefits

• PTO
• Stock Options
• Health Benefits
• Base salary range: $140,000–$170,000, commensurate with experience