Research Assistant Professor - Machine Learning and AI for Brain Mapping

Position Responsibilities

• Lead the adoption of rigorous scientific ML/AI practices for the cluster's modeling and analysis work, including reproducible experiment tracking, principled model evaluation, validation against expert-curated ground truth, and transparent reporting of methods, data, and results.
• Design, develop, and evaluate machine learning and AI methods for the rat-to-atlas mapping pipeline, including ML-based image registration, segmentation, and feature extraction applied to light-sheet 3-D microscopy data, and automated atlas-based annotation.
• Build cross-layer query capabilities over the cluster's stack of atlas-registered data, enabling integrated interrogation of any mapped region across multiple data modalities (gene expression, connectivity, physiology, behavioral activation, and others).
• Develop ML/AI methods grounded in the Brain Maps 4.0 and Chemopleth 1.0 frameworks, using expert-curated maps as ground-truth training and validation data, with attention to interoperability with international neuroinformatics infrastructure such as EBRAINS and the BrainGlobe ecosystem.
• Collaborate with cluster-hire colleagues in behavioral neuroscience, circuit imaging and mapping, and research software engineering to translate scientific questions into ML/AI approaches and to support multi-modal data integration and atlas development.
• Contribute to peer-reviewed publications and federal grant applications describing the cluster's ML/AI methods, datasets, and modeling outputs, including the open-access digital atlas of brain reward circuits.
• Contribute to the Brain Mapping & Connectomics (BM&C) undergraduate teaching laboratory by introducing AI-based mapping methods into its curriculum and mentoring students as contributors to the cluster's research pipeline.
• Engage with UTEP's Institute for Applied AI Innovation (AAII) and the M.S. in Artificial Intelligence program through mentorship of graduate researchers, supervision of student capstone or thesis projects drawn from the cluster's atlas work, and participation in programmatic activities.

Job Requirements

• Ph.D. in computer science, machine learning, biomedical engineering, computational neuroscience, applied mathematics, computational or mathematical sciences, or a related field; or a Master's degree with substantial professional ML/AI research experience.
• Experience with rigorous ML/AI research practices, including reproducible experiment tracking, principled model evaluation, validation against ground truth, and transparent reporting.
• Demonstrated research experience in computer vision and deep learning applied to biological microscopy data - including image registration, segmentation, and feature extraction with architectures such as U-Net and its 3-D variants in modern ML frameworks (e.g., PyTorch) - evidenced by peer-reviewed publications, preprints, or open-source contributions.
• Demonstrated experience with spatial-AI or related spatial-data methods (e.g., multi-layer spatial queries, spatial statistical modeling, or atlas-based registration of multi-modal data).
• Experience with the technical infrastructure for scalable biomedical imaging research, including handling large volumetric microscopy datasets (e.g., light-sheet or serial-section reconstructions of whole rodent brains; memory-efficient I/O, tile-based or chunked processing, multi-resolution formats such as OME-Zarr) and GPU computing on cloud or HPC environments.
• Experience mentoring or training undergraduate or graduate students in ML/AI methodology, including supervision of student modeling projects.
• Demonstrated interest in or experience with neuroscience, biomedical imaging, or related scientific domains.
• Demonstrated ability to work in interdisciplinary teams that connect ML/AI methodology to scientific questions and experimental data.

Preferred Qualifications

• Experience working in academic or research-intensive environments, including open-source ML or scientific projects.
• Familiarity with neuroscience or biomedical data formats and standards (e.g., NIfTI, BIDS, OME-TIFF).
• Foundation in classical computer vision and image-processing methods, complementing modern deep-learning approaches.
• Familiarity with the deep-learning and analysis tool ecosystem used in mesoscale rodent brain mapping - spanning cellular/sub-cellular segmentation (e.g., Cellpose, StarDist), whole-brain mesoscale pipelines (e.g., cellfinder, brainreg, brainmapper, DeepSlice), and image inspection platforms (e.g., Napari, Fiji/ImageJ, QuPath).
• Experience with model interpretability methods and validation against expert-curated ground truth annotations.
• Familiarity with the BrainGlobe ecosystem, EBRAINS, NIH BRAIN Initiative resources, and Brain Maps 4.0 or analogous mesoscale chemoarchitectural atlases.
• Additional familiarity with graph theory and connectomic analyses, network neuroscience, or NLP-based biomedical literature mining - complementary methodologies that may support collaboration with external network-neuroscience and informatics partners.
• Track record of independent grant submissions or co-authored funded proposals related to ML/AI, computational neuroscience, or scientific computing.
• Experience teaching, mentoring, or supervising graduate research within an AI research institute or master's-level AI program.