Senior Principal AI/ML Engineer - Research

- Architect and implement Mayos multimodal EMR representation AI architecture encompassing text, imaging, waveform, structured data, temporal sequences, and multi-visit trajectories. - Develop graph-based representations and knowledge graphs linking patients, events, attributes, clinical concepts, and embeddings. - Integrate graph reasoning, vector similarity search, and hybrid vector-graph pipelines for retrieval-enhanced models and agentic reasoning. - Establish standards for temporal modeling, drift-aware embeddings, and alignment across encounters. - Construct large-scale embedding pipelines utilizing transformer models, contrastive learning, graph neural networks, and hybrid architectures. - Create effective query layers employing vector stores and graph databases. - Develop interpretable embedding diagnostics, attribution tools, and graph-based audits to facilitate safe clinical implementation. - Investigate and apply methods for elucidating similarity, graph traversals, temporal changes, and patient-neighborhood reasoning. - Collaborate with AI researchers on specialty-specific embeddings, representation refining, and research prototypes. - Work alongside clinicians to implement clinically significant features, phenotypes, and longitudinal concepts. - Provide scientific insights to the Foundational Model Science Program to align representations with model architectures. - Lead the Reasoning EMR Representation team as the founding technical advisor. - Mentor junior scientists and engineers; build a specialized team focusing on representation learning and graph-based reasoning.