Fraud Data Scientist

About the Role

As a Fraud Data Scientist, you will be at the front lines of protecting our ecosystem from sophisticated financial fraud and abuse. You will join a high-impact team operating in a data-rich, high-frequency environment where seconds matter.

In this role, you will take ownership of the end-to-end machine learning lifecycle—from uncovering complex fraud patterns to deploying highly scalable, real-time models into production. You will collaborate closely with Engineering, Product, and Risk Operations to build robust defenses that balance strict security with a seamless user experience.

What You Will Be Doing

• Model Development & Deployment: Design, train, and deploy advanced machine learning models (e.g., gradient boosting, anomaly detection, graph networks) to detect and mitigate fraud in real-time.
• Production Ownership: Take full ownership of putting models into production systems, ensuring low-latency execution and high reliability.
• Agentic Workflows: Research, build, and implement Agentic flows and LLM-driven orchestration to automate multi-step fraud decisioning, logic routing, and investigation paths.
• Adversarial Analysis: Conduct deep-dive exploratory analysis on massive datasets to identify emerging fraud vectors, loops, and coordinated attacks.
• Feature Engineering: Build and optimize real-time streaming and batch features to improve model signal and precision.
• Experimentation & Monitoring: Design rigorous shadow-testing and A/B testing frameworks for new models. Set up continuous monitoring pipelines to catch data drift and performance degradation early.

Requirements

• Experience: Minimum of 3 years of applied Data Science experience with a proven track record across fintech domains, with experience in fraud, risk, or payments preferred.
• Production Expertise: Proven, hands‑on experience deploying and maintaining machine learning models in high‑traffic production environments is required, with real‑time experience preferred.
• Data Science Tech Stack: Expert-level Python programming (Pandas, NumPy, Scikit‑Learn, XGBoost/LightGBM) and exceptional SQL skills for querying massive, complex datasets.
• Data Environment: Robust experience working within cloud data environments like Databricks, and querying/manipulating large-scale datasets in data warehouses like BigQuery.
• Orchestration & MLOps: Practical experience with machine learning lifecycle and orchestration tools, such as MLflow and Airflow.
• Business-Impact Focus: A strong ability to translate raw model results into real-world business outcomes. You know how to balance technical model performance (precision/recall) with financial impact, operational realities, and the user experience.

#J-18808-Ljbffr…