Stanford University is launching an interdisciplinary Neuro-AI project dedicated to building a foundation model of the brain. This endeavor will involve multiple labs and faculty across the Stanford campus, including the Wu Tsai Neurosciences Institute, Stanford Bio-X, and the Human-Centered Artificial Intelligence Institute. Leveraging cutting-edge advances in electrophysiology and machine learning, this project aims to create a functional "digital twin" -- a model that captures both the activity dynamics of the brain at cellular resolution and the intelligent behavior it generates.

We are seeking a highly skilled Computer Vision Engineer (Software Developer 2) to join our interdisciplinary team. This role will be pivotal in bridging the gap between neuroscience and artificial intelligence by developing and implementing cutting-edge computer vision techniques to analyze and annotate complex visual datasets. The ideal candidate will have a strong background in computer vision, deep learning, and mathematical modeling, with a keen interest in applying these skills to advance our understanding of neural processing in the visual cortex.

This position promises a vibrant and cooperative atmosphere within the laboratories of Andreas Tolias (https://toliaslab.org), Tirin Moore (https://www.moorelabstanford.com) and other labs at Stanford University renowned for their expertise in perception, cognition, pioneering neural recording techniques, computational neuroscience, machine learning, and Neuro-AI research.

Role & Responsibilities:

* Design and implement robust machine learning pipelines for processing and analyzing large-scale video datasets

* Curate and refine datasets of natural videos for use as stimuli in cutting-edge neuroscience experiments

* Implement and adapt state-of-the-art computer vision algorithms to generate comprehensive annotations and metadata for video datasets, including object segmentation, categorization, optic flow, depth estimation, and semantic scene understanding

* Develop and apply mathematical methods to quantify and optimize the coverage of natural scene statistics/manifolds within curated datasets

* Collaborate closely with the modeling team to integrate featurized datasets into a large-scale multi-modal foundation model of the visual cortex

* Contribute to the development of novel algorithms that bridge computer vision techniques with neuroscientific insights