Senior Fraud Data Scientist — Production ML & Investigations

DataVisor; Calgary; Presencial; CAD 168 000 - 210 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Stock Options

Health Benefits

PTO

Resumo da oferta

DataVisor is seeking a Senior-Level Data Scientist to join our Fraud Detection team. You will build production ML models, lead investigations into fraud cases, and translate findings into actionable detection improvements. This dual-track role blends modeling with hands-on case work.

You'll work on large-scale data, implement advanced features, and collaborate across product, engineering, and operations to defend customers against evolving fraud threats in a fast-paced, data-driven environment.

Qualificações

• Master's or PhD in CS, Statistics, Mathematics, or related field.
• 3+ years in fraud detection or risk domain.
• Strong ML model knowledge (LR, gradient boosting, etc.).
• Production ML lifecycle experience.
• Proficient in Python and SQL; PySpark a plus.
• Excellent communication for cross-functional teams.
• Experience with large-scale data tools and cloud platforms.

Responsabilidades

• Lead end-to-end fraud detection model development.
• Develop features from large-scale, multi-dimensional data.
• Perform live investigations and generate reports.
• Produce fraud trend reports for customers.

Conhecimentos

Python

SQL

Data Analysis

Communication

Team Collaboration

Problem Solving

Formação académica

Master's or PhD in CS/Statistics/Mathematics

Ferramentas

Spark

Hadoop

AWS/GCP/Azure

PySpark

Descrição da oferta de emprego

DataVisor is seeking a Senior-Level Data Scientist to join our Fraud Detection team. You will build production ML models, lead investigations into fraud cases, and translate findings into actionable detection improvements. This dual-track role blends modeling with hands-on case work.

You'll work on large-scale data, implement advanced features, and collaborate across product, engineering, and operations to defend customers against evolving fraud threats in a fast-paced, data-driven environment.