Intern - Graph & Compliance DS

Join our applied research team for a summer internship focused on advancing machine learning techniques for Identity Graph applications. In this role, you will work on real-world graph learning problems centered on modeling relationships across entities, improving graph-based representations, and developing methods that support high-impact decision systems.

This internship goes beyond academic experimentation — you will design, implement, and evaluate production-relevant machine learning solutions that directly contribute to our Identity Graph initiatives. Areas of work may include node representation learning, node classification, and link prediction on large-scale graph data.

You will collaborate closely with senior data scientists and engineers to prototype new ideas, conduct rigorous experiments, and help translate research into scalable solutions.

What You’ll Work On

• Investigating machine learning approaches for Identity Graph problems
• Building and evaluating models for node classification and link prediction
• Applying node embedding and graph representation learning methods to relational datasets
• Exploring novel architectures, objectives, and evaluation strategies
• Performing analysis to understand model performance and failure cases
• Contributing to technical documentation and research discussions

Qualifications

• Current Master’s or PhD student in Computer Science, Machine Learning, Statistics, Mathematics, or a related field
• Strong foundation in machine learning
• Experience with graph ML methods, especially node embeddings and link prediction
• Familiarity with graph neural networks or related graph representation learning methods is a plus
• Strong Python programming skills; experience with PyTorch or TensorFlow preferred
• Strong analytical, problem-solving, and communication skills