Senior Data Scientist - AI and ECG

The Division of Cardiovascular Medicine at the University of Michigan is expanding a nationally and internationally funded research program at the cutting edge of cardiovascular medicine. Led by Drs. Venkatesh Murthy and Sascha Goonewardena - whose work has appeared in leading journals including NEJM AI, JAMA, and Circulation - the program fuses artificial intelligence, advanced cardiac imaging, multiomics (proteomics, metabolomics, and genomics), and cardiometabolic disease biology to develop precision diagnostics and identify novel therapeutic approaches, with a particular focus on coronary microvascular disease and other cardiovascular conditions that disproportionately affect women and remain poorly served by existing diagnostic tools. This is a rare opportunity to join a high-impact, well-funded program doing science that matters., This position serves as the primary AI and ECG computational scientist for the program. The incumbent will build and train deep learning foundation models and drive the computational work that connects cardiac electrical signatures to biological disease mechanisms. This is an engineering and infrastructure-focused role; the incumbent builds and optimizes the models and data systems that power the program's AI-driven analyses. This is one of two senior data scientist roles; the two positions serve complementary, non-overlapping functions., * Develop, train, and refine deep learning foundation models (including transformer and self-supervised architectures) for ECG-based detection and endotyping of cardiometabolic disease

• Assemble, harmonize, clean, and catalog large-scale, heterogeneous ECG datasets from multiple internal and external sources and formats
• Build and maintain reproducible data processing pipelines, data loaders, and PostgreSQL-based data management infrastructure
• Evaluate model performance, document methods, and prepare written and code-based analytical reports (Python)
• Contribute to manuscripts, grant reports, and presentations
• Collaborate with collaborative network partners and other research collaborators on code, computational workflows, and data harmonization
• Other duties as assigned, Michigan Medicine conducts background screening and pre-employment drug testing on job candidates upon acceptance of a contingent job offer and may use a third party administrator to conduct background screenings. Background screenings are performed in compliance with the Fair Credit Report Act. Pre-employment drug testing applies to all selected candidates, including new or additional faculty and staff appointments, as well as transfers from other U-M campuses.

• Masters or doctoral degree in computer science, electrical engineering, biomedical engineering, computational biology, statistics with an AI/ML focus, data science, or a closely related quantitative field
• Demonstrated experience developing and training deep learning models, preferably in a biomedical or physiological signal context
• Proficiency in Python and deep learning frameworks (PyTorch preferred; TensorFlow acceptable)
• Experience with large-scale, heterogeneous data harmonization and processing pipelines spanning multiple source formats
• Familiarity with self-supervised, semi-supervised, or foundation model architectures (e.g., transformers, masked autoencoders)
• Proficiency in SQL, preferably PostgreSQL, for data querying and management
• Experience with high-performance computing environments, including Slurm-based job scheduling
• Strong organizational skills and attention to detail
• Ability to prepare and present written and code-based (Python or R) analytical reports
• Strong scientific communication skills; ability to contribute to manuscripts and grant reports, * Experience with electrocardiographic (ECG) or other physiological waveform data
• Experience with multimodal data integration, particularly combining physiological signals with cardiac imaging data
• Familiarity with clinical data infrastructure (EHR, DICOM, HL7/FHIR)
• Experience with transfer learning or domain adaptation across heterogeneous datasets
• Track record of peer-reviewed publications or preprints in machine learning, AI, or biomedical informatics
• Familiarity with cardiovascular physiology or cardiology research
• Experience with Git and reproducible research practices
• Familiarity with cloud computing environments (AWS, GCP, or Azure)

Michigan Medicine improves the health of patients, populations and communities through excellence in education, patient care, community service, research and technology development, and through leadership activities in Michigan, nationally and internationally. Our mission is guided by our Strategic Principles and has three critical components; patient care, education and research that together enhance our contribution to society., Michigan Medicine is one of the largest health care complexes in the world and has been the site of many groundbreaking medical and technological advancements since the opening of the U-M Medical School in 1850. Michigan Medicine is comprised of over 30,000 employees and our vision is to attract, inspire, and develop outstanding people in medicine, sciences, and healthcare to become one of the world?s most distinguished academic health systems. In some way, great or small, every person here helps to advance this world-class institution. Work at Michigan Medicine and become a victor for the greater good., We, the staff and faculty of the U-M Cardiovascular Center (CVC) team, are committed to advancing medicine and serving humanity through living and teaching our core values of Respect and Compassion; Collaboration; Innovation; and Commitment to Excellence. Each CVC employee is expected to understand and demonstrate that in every interaction we represent our entire organization in the care we provide and in the courtesies we extend to patients, families, and each respective team member. The CVC is dedicated to partnering with patients and families to deliver the safest and highest quality of health care. The Division of Cardiovascular Medicine is firmly committed to advancing inclusion, diversity, equity, accessibility, and belonging, which are core to the culture and values of the Medical School Office of Research. Our community supports recruiting and cultivating a diverse workforce as a reflection of our commitment to serve the diverse people of Michigan and the world. We strive to create a work culture where each team member feels respected, valued, and safe.