Staff Data Scientist - Fraud & Risk

Responsibilities

• Design, develop, and implement advanced deep learning models, including transformers, CNNs/RNNs, and graph learning algorithms, to address complex fraud and risk challenges.
• Build and optimize models using a variety of input data types, including tabular data, natural language, point clouds, and images.
• Lead the end-to-end machine learning lifecycle: data exploration, feature engineering, model training, evaluation, deployment, and monitoring in production environments.
• Take ownership of project outcomes, data quality, and delivery timelines; proactively escalate issues and work collaboratively to resolve challenges.
• Mentor and share knowledge with peers and junior data scientists, fostering a culture of experimentation, rapid iteration, and continuous learning.
• Collaborate cross-functionally with Product, Engineering, and Risk teams to define data requirements and drive insights that guide strategic decisions.
• Conduct in-depth research to explore new data sources and develop novel algorithms that advance the state of the art in fraud detection.
• Present findings and recommendations to technical and executive stakeholders with clarity and influence.
• Stay current with advancements in AI and machine learning, applying innovative approaches to real-world problems.

Requirements

• Master’s or PhD in Computer Science, Statistics, Applied Mathematics, Data Science, or a related field; or equivalent professional experience.
• 8+ years of experience in data science, machine learning, or related fields, ideally in a high-growth tech or fintech environment.
• Experience in fraud prevention, risk modeling, or identity verification.
• Hands-on experience developing and deploying deep learning models (such as transformers, CNNs/RNNs, and graph learning).
• Experience working with diverse data modalities, such as tabular data, text/language, point clouds, and images.
• Strong proficiency in Python, SQL, and major ML libraries/frameworks (e.g., PyTorch, TensorFlow, scikit-learn).
• Deep understanding of machine learning algorithms, model evaluation techniques, and data pipeline development.
• Experience with model deployment and monitoring in production environments (real-time model inferencing is a plus).

Nice-to-Haves

• Experience with LLMs and Agentic AI framework/infrastructure (e.g., LangChain, LangGraph, Ray).