The Carmichael lab (https://idc9.github.io/) is looking for a postdoctoral fellow interested in developing either machine learning algorithms for high-resolution histopathology imaging/spatial-profiling data in combination with other modalities (e.g. radiology, sequencing, or text) or large language model-based approaches for extracting information from clinical notes at scale. The lab's goal is to address the key technical challenges holding back the impact of AI in Pathology/Oncology in order to improve diagnostic precision, increase access to state-of-the-art care for patients around the world, uncover novel biomarkers for disease prognosis/therapeutic response, and advance basic scientific investigation into disease processes. The ideal candidate will have a strong background in both the mathematical and software sides of machine learning, with the ability to design and implement novel artificial intelligence algorithms. Examples of research directions could include: multimodal foundational models for biomedical data, deep-learning architectures for high-resolution (e.g. gigapixel) imaging, or high-dimensional statistical approaches for analyzing spatial transcriptomic data.

This role involves close collaboration with an interdisciplinary team of data scientists/clinicians and working with unique datasets from multiple academic medical centers (e.g. UNC, UCSF, Mayo Clinic, Memorial Sloan Kettering, etc). Lab dedicated GPU workstations/servers and cloud compute credits are available along with CPU/GPU nodes provided by the university. The expected outcomes of the position are: lead 1-2 major projects, contribute to other projects, collaborate with trainees (computational undergrad/masters/PhD students + clinical residents/fellows), write publications, and release open-source software. Projects may be focused on disease-specific translational research or core machine learning methodology development. This role is well suited for candidates aiming to launch an ambitious career at the intersection of machine learning and biomedical research in academia or industry.

In addition to recent PhD graduates, we welcome candidates from industry looking to make a pivot. 

A strong background in both the mathematical and software sides of machine learning/data science (especially deep-learning, computer vision, or natural language processing) though exceptional candidates with other experience will be considered. Track record of publications in premier technical and/or biomedical venues. Previous experience with biomedical research is appreciated, but not required.