- Develop and evaluate AI-based biomarkers using whole-slide images, clinical variables, and molecular data to predict patient outcomes, treatment benefit, and molecular traits.
- Contribute to self-supervised foundation models and downstream models, including multiple-instance learning, time-to-event or hazard models, segmentation, and classification.
- Develop and evaluate methods to improve model robustness and reproducibility across scanners, institutions, staining protocols, and patient populations.
- Explore interpretability methods to explain model decisions and support clinician trust and actionable model improvements.
- Build and improve tools and workflows for reproducible model development, experimentation, validation, and deployment.
- Perform model evaluation and analysis, communicate findings, and document experiments and technical decisions.
- Collaborate with ML scientists and engineers and with product, biostatistics, clinical development, and regulatory and quality partners.
- Support regulatory and quality documentation related to AI model development and validation.
- Contribute to peer-reviewed publications, conference presentations, and external academic or industry collaborations.
PythonMachine LearningPyTorch+2 more