Data Scientist

Develop, maintain, and improve graph-native machine learning models (GNNs, embeddings) for fraud, collusion, and identity risk detection.

Collaborate under senior data scientist guidance to design, train, and evaluate statistical, AI/ML, and deep learning models specifically for fraud and risk domains.

Own related tasks such as data cleaning, experiments, light data pipeline work, and producing production-quality ML/statistical code with clear documentation.

Bachelor's or Master's degree in Machine Learning, Computer Science, Mathematics, Statistics, or related field.

1 to 3 years of experience in data science, AI, or ML engineering roles; internships with shipped work count.

Strong proficiency in Python and working knowledge of SQL; exposure to cloud platforms (AWS, Databricks, Azure) is a plus.

Experience with production-adjacent ML model deployment or development, ideally with fraud, risk, payments, or compliance data, but strong fundamentals may compensate.

Operates comfortably with ambiguous, unlabeled data and takes initiative to research independently.

Has foundational or applied knowledge of graph-based machine learning concepts (GNNs, graph algorithms), even via coursework or personal projects.

Prefers working in fast-paced environments focusing on speed, ownership, and measurable impact rather than strict processes or predictability.