We're Hiring! Postdoctoral Fellow in Multimodal Medical AI
Overview: Postdoctoral Fellow in Multimodal Medical AI (M2AI) Lab (Hybrid-US)
Our team at the University of California, San Francisco (UCSF) is seeking a motivated postdoc to join the Multimodal Medical AI (M2AI) lab. The M2AI lab is embedded within the UCSF Division of Clinical Informatics and Digital Transformation (DoC-IT), UCSF Department of Neurological Surgery, and the Bakar Computational Health Sciences Institute (BCHSI). The lab is dedicated to advancing the current state-of-the-art methodology in deep learning and AI to enable effective processing of multimodal electronic health record (EHR) data and utilizing these techniques to improve quality, delivery, and access to clinical care.
DoC-IT, within the Department of Medicine, serves as the academic home for applied clinical informatics at UCSF. The division also is as a coordinating entity with key internal and external digital stakeholders across all UCSF mission areas, schools, departments, and divisions. Home to UCSF’s Clinical Informatics Fellowship, DoC-IT partners with other UCSF entities to develop new education and training programs. Lastly, the division forges novel partnerships with UCSF health systems, other UCSF affiliates, and industry partners to ensure that our work has a real-world impact. BCHSI is a pioneer in developing health data infrastructure for advanced AI research.
The UCSF Information Commons effort, which is a collaboration between BCHSI and UCSF IT, supports research-specific provisioning of de-identified patient data for over 4 million patients at UCSF, which is further linked with data from all University of California hospitals. The M2AI lab engages in many cross-campus collaborations with UC Berkeley. The lab is affiliated with the UC Berkeley-UCSF joint graduate program in Computational Precision Health and the UCSF Biological and Medical Informatics graduate program.
Job Description
UCSF is seeking a highly motivated postdoctoral fellow to join the M2AI lab and lead the development and application of multimodal foundation models for medicine to improve diagnostic workflows and understand disease trajectories to optimize treatment decisions. This includes developing a new methodology and adapting existing technology to incorporate the nuances of healthcare data and validating the developed solutions within clinical workflows. You will work closely with faculty, staff, and fellows at DoC-IT, BCHSI, and the Department of Neurosurgery, while jointly collaborating with clinical teams at UCSF. You will also be able to gain valuable experience in the development of AI/ML solutions within real-world clinical settings while building cross-disciplinary collaborations. Publication and dissemination of the work in technical and medical informatics venues is also expected.
The initial appointment will be for 1-2 years, with an opportunity for extension pending performance and availability of funds.
UC San Francisco seeks candidates whose experience, teaching, research, or community service has prepared them to contribute to our commitment to diversity and excellence. The University of California is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, age, or protected veteran status.
Job Requirements
Required Qualifications:
- Currently holds or is in the process of obtaining a PhD in Computer Science or a related field.
- First-authored publications at leading conferences such as ACL, NeurIPS, ICLR, ICML, AAAI, or in prominent medical informatics venues like NEJM-AI, Nature, JBI, or JAMIA.
- Extensive experience in deep learning (Python or related languages), experience with SQL.
- Effective communication and interpersonal skills.
- Self-motivated and able to work independently and as part of a team. Able to lead research projects, learn effectively, and meet deadlines.
- Demonstrated independent research thinking and broad problem-solving skills.
- Passion for solving pressing challenges in healthcare with cutting-edge AI research.
Preferred Qualifications:
- Experience working with healthcare data such as electronic health record (EHR) data, clinical notes, or radiology images.
- Experience with developing vision foundation models, vision-language models, or large-language models for medical data.
- Demonstrated contributions in open-source repositories.
- Ability to work with multi-disciplinary teams.
How to Apply
Please email a cover letter describing your qualifications for the position and a current CV to: [email protected].
Questions about the position can be directed to: [email protected]
Applications will be screened on a rolling basis until the position is filled.