Data Scientist (Fraud)

Join Billie, a fast-growing fintech company, as a Fraud Data Scientist. In this role, you will design and build machine learning solutions to prevent fraud, impacting Billie's bottom line. You will own the end-to-end modeling lifecycle, collaborate with various teams, and share knowledge across the team. Enjoy benefits such as flexible work arrangements, 30 days of vacation, and an individual training budget.

• Design and build robust, scalable machine learning solutions that prevent fraud, with a direct and measurable impact on the company's bottom line.
• Own the end-to-end modeling lifecycle: defining the analytical approach, testing hypotheses, and deploying models that capture complex debtor behavior and emerging fraud patterns.
• Collaborate with data and software engineers, analysts, and product managers to improve decision logic, integrate new data sources, and extend system functionality.
• Sharp problem-solving skills, with the ability to translate complex business challenges into clean, efficient, and scalable technical requirements
• Deep expertise in classification models (classical and deep learning), anomaly detection, and graph-based methods (e.g., graph neural networks, entity-link analysis)
• Proven ability to manage stakeholders across technical and non-technical functions, aligning technical roadmaps with business priorities
• Proven advanced proficiency in Python (e.g. pandas, scikit-learn, xgboost) and SQL (Snowflake, Postgres, or MySQL)
• Strong communication skills, with a track record of using data to influence strategy and drive cross-functional engagement
• 3-5+ years in a quantitative or machine learning role, ideally in fintech or another high-transaction environment. Direct experience in fraud prevention or risk modeling is strongly preferred
• Hands-on experience productionizing ML services, with a strong grasp of modern MLOps concepts such as containerization (Docker/Kubernetes) and event-driven architectures
• Experience with ML orchestration frameworks such as Metaflow, Apache Flink, or similar MLOps tooling
• Experience implementing LLM-based workflows (e.g., agentic pipelines, retrieval-augmented generation, or LLM-assisted feature extraction), particularly applied to fraud detection or risk signals