2027 Winter Graduate Co-op - Clinical Affairs AI/ML

The Opportunity

This position works out of our location in the Abbott's Electrophysiology (EP) business in St. Paul, MN. In Abbott's Electrophysiology (EP) business, we're advancing the treatment of heart disease through breakthrough medical technologies in atrial fibrillation, allowing people to restore their health and get on with their lives. As the PhD Co-op, you'll have the chance to focus on clinical research applications including patient recruitment forecasting, prediction of outcomes following electrophysiology procedures, and generation of novel evidence to support scientific publication and future product innovation.

What You'll Work On

• Design, develop, train, evaluate and fine-tune predictive models for clinical trial enrollment forecasting, clinical outcomes and other clinical applications.
• Evaluate model performance using clinically relevant endpoints and validation methodologies.
• Build data pipelines for harmonizing and curating diverse clinical and procedural datasets.
• Perform data quality assessments, feature engineering, and model-ready dataset creation.
• Integrate and analyze large multimodal structured or unstructured datasets including medical imaging, clinical records, procedural data, adverse event data, and clinical trial datasets.
• Develop data pipelines, algorithms, and visualization tools.
• Track metrics and document results to improve model accuracy.
• Apply statistical, predictive, and generative AI techniques.
• Collaborate with clinical scientists to identify clinically meaningful questions, endpoints, and model performance criteria.
• Prepare technical reports, presentations, and recommendations.
• Collaborate with cross-functional stakeholders.
• Support scientific abstracts and publications.

Expected Deliverables

• Validated and functional predictive model(s) and reproducible prototype(s) with documented performance metrics and recommendations for future clinical or operational applications.
• Leadership presentation of findings and recommendations.
• Technical documentation supporting future development.
• Contribution to a scientific abstract or publication draft.

Required Education

Currently enrolled in a Master's or PhD program in Computer Science, Bioinformatics, Computational Biology, Health Informatics, Engineering, or related field. PhD candidates preferred.

Required Qualifications

• Advanced proficiency in Python required; experience with R, SQL, MATLAB, Julia, or other analytical programming languages preferred.
• Experience with software development, version control, and code documentation.
• Familiarity with core machine learning concepts, statistics, and frameworks
• Experience developing machine learning or advanced analytical models.
• Experience using Git for version control and familiarity with shell-based or cloud development environments.
• Knowledge of statistical analysis, predictive modeling, and data mining.
• Experience managing and analyzing large datasets.
• Strong problem-solving abilities and a demonstrated eagerness to research and learn new AI technologies independently.

Preferred Qualifications

• Experience with deep learning, NLP, generative AI, or large language models.
• Familiarity with libraries such as PyTorch, TensorFlow/Keras, Scikit-learn or XGBoost/LightGBM preferred.
• Experience with multimodal AI, foundation models, or fusion methods combining imaging and structured clinical data.
• Established and shareable GitHub repository
• Experience working with cardiac CT, cardiac MRI, echocardiography, fluoroscopy, DICOM data, or other cardiovascular imaging datasets.
• Experience with longitudinal data analysis, survival analysis, risk prediction modeling, or time-to-event methodologies
• Publication record or demonstrated research excellence.

Professional Competencies

• Strong analytical and problem-solving skills.
• Ability to work independently and manage multiple priorities.
• Strong written, verbal, and presentation skills.
• Ability to communicate complex technical concepts effectively.
• Collaborative mindset and intellectual curiosity.