Open Postdoctoral position, faculty mentor Ehsan Adeli

Important Info

Faculty Sponsor First name:

Ehsan

Faculty Sponsor Last Name:

Adeli

Other Mentor(s) if Applicable:

Daniel Yamins

Stanford Departments and Centers:

Psychiatry

Group or Departmental Website:

https://stai.stanford.edu

https://neuroailab.stanford.edu/

https://neuroscience.stanford.edu/

Does this position pay above the required minimum?:

Yes. The expected base pay range for this position is listed in Pay Range field. The pay offered to the selected candidate will be determined based on factors including (but not limited to) the qualifications of the selected candidate, budget availability, and internal equity.

Pay Range:

$80,000 - $85,000

Postdoctoral Research Fellow - Computational Neuroscience and Brain Foundation Models at Stanford University

We are recruiting a highly motivated Postdoctoral Research Fellow to join an interdisciplinary effort at Stanford University focused on building next-generation Brain Foundation Models as part of the Stanford Digital Brain Project. The fellow will work closely with Professor Ehsan Adeli and Professor Dan Yamins, as well as researchers across the STAI Lab and NeuroAI Lab, within both the Stanford Wu Tsai Neurosceince Institute and the Stanford Institute for Human-Centered AI (HAI).

Research Focus

The fellow will lead computational modeling efforts to develop large-scale, multimodal models of the human brain. The work will involve integrating brain imaging, neural signals, behavioral, cognitive, genetic, and clinical data to model brain structure, function, and dynamics across individuals and populations.

Key Responsibilities

The postdoctoral fellow will:

Develop and implement advanced AI and computational neuroscience models for brain structure and function.
Lead modeling efforts for multimodal brain foundation models.
Work with fMRI, structural MRI, diffusion MRI, EEG, and other neural signal modalities.
Build scalable training and evaluation pipelines for large neuroimaging datasets.
Collaborate closely with researchers across AI, neuroscience, psychiatry, biomedical imaging, and cognitive science.
Lead high-impact publications and contribute to grants, workshops, and collaborative project development.

Environment

The fellow will join a highly collaborative research ecosystem spanning the Stanford Translational AI (STAI) Lab, the NeuroAI Lab, the Stanford Wu Tsai Neurosceince Institute, and the Stanford Institute for Human-Centered AI (HAI), with opportunities to work with faculty, students, postdocs, and clinicians across Stanford. This position offers a unique opportunity to help shape a major research direction at the intersection of AI, neuroscience, and human health.

Required Qualifications:

A Ph.D. in computer science, computational neuroscience, biomedical engineering, electrical engineering, cognitive science, applied mathematics, physics, or a related field.
Strong computational background and hands-on experience building AI/ML models.
Expertise in modern architectures such as transformers, self-supervised learning, multimodal learning, generative models, graph neural networks, or foundation models.
Experience with structural and/or functional brain modeling.
Familiarity with neuroimaging and neural signal processing tools, including fMRI, structural MRI, diffusion MRI, EEG, or related modalities.
Strong publication record in AI, machine learning, computational neuroscience, or neuroscience venues, such as NeurIPS, ICML, ICLR, ACL, CVPR, Nature Neuroscience, Neuron, or related venues.
Demonstrated ability to work in multidisciplinary teams and communicate across scientific domains.

Preferred Experience:

Strong candidates may also have experience with:

Large-scale neuroimaging datasets.
GPU-based model training and distributed computing.
Brain connectivity modeling, representational analysis, or computational cognitive neuroscience.
Clinical neuroscience applications, including neuropsychiatric, neurodevelopmental, or neurodegenerative disorders.
Open-source software development and reproducible research pipelines.