Data Scientist (Fraud & Risk)

Join our Fraud & Risk Data Science team as a Data Scientist II. In this role, you will design, develop, and implement advanced deep learning models to address complex fraud and risk challenges. You will have autonomy in your day-to-day work and play an important role in driving functional productivity and project success. This position offers the opportunity to contribute to diverse projects and collaborate within a supportive, high-performing team.

• Design, develop, and implement advanced deep learning models to address complex fraud and risk challenges.
• Participate in all stages of the machine learning lifecycle, including data exploration, feature engineering, model training, evaluation, and deployment.
• Collaborate effectively across teams, sharing knowledge and learning from diverse perspectives to drive results.

• Demonstrated ability to collaborate in a diverse, cross-functional team environment
• Experience with LLMs and Agentic AI framework/infrastructure (e.g., LangChain/LangGraph/Ray) is a plus
• Bachelor’s degree with substantial related experience, Master’s degree with relevant experience, or equivalent work background in Computer Science, Statistics, Mathematics, Engineering, or a related field
• Excellent written and verbal communication skills
• Foundational understanding of machine learning algorithms, model evaluation techniques, and data pipeline development
• Proficiency in Python and major ML libraries/frameworks (e.g., PyTorch, TensorFlow, scikit-learn)
• Experience with model deployment and monitoring in production environments (specific experience with real-time model inferencing is a plus)
• Experience in fraud prevention, risk modeling, or identity verification is a plus
• Strong problem-solving skills, with the ability to work independently on straightforward tasks and contribute effectively to project objectives
• 2-4 years of hands-on experience developing and deploying deep learning models (such as transformers, CNNs, and LSTMs)
• Experience working with diverse data modalities, such as tabular data, text/language, point clouds, and images