Postdoctoral Researcher - AI/ML in Medicine and Biology

A postdoctoral fellowship is available at the Stanford University School of Medicine focused on developing and applying machine learning to population-scale clinical and biological data. To receive full consideration, please follow the instructions at the end of this notice.Research areas include, but are not limited to:Training unimodal and multimodal foundation models on electronic health records and other healthcare data modalities (e.g., waveform and vital sign data).Combining clinical information with biological omics data (e.g., genomics, proteomics, and metabolomics) to gain biological and clinical insights through biomarker discovery, predictive modeling, and patient stratification.Studying treatment response and drug effects with real-world data, causal inference, and in silico clinical trials.The outcomes and disease areas under study in the lab are broad, covering intraoperative and perioperative outcomes, critical care outcomes, adult and pediatric health, women’s health (fertility, menopause, and pregnancy outcomes), cancer outcomes, and cardiovascular, neurological, and autoimmune diseases. We are always interested in expanding our research horizons.The lab has a strong translational focus and deep ties to clinical research teams across Stanford and other institutions, with the aim of moving projects developed in the lab into validation studies with clinicians and end users and, ultimately, into real-world use.This is a unique opportunity to apply ML in unconventional and paradigm-shifting research with the potential to directly and broadly impact human lives. By joining our research group, you will:Have direct access to millions of patient records and multiomics datasets from thousands of patients, with broad opportunities to obtain specialty datasets through collaborations with groups across Stanford.Have access to extensive computational resources, including several dedicated lab servers and highly flexible, real-time use of NVIDIA H200 GPUs.Work in a highly collaborative environment with researchers from diverse backgrounds in medicine, biological sciences, and computer science.Collaborate with world-leading experts at Stanford University across the spectrum of AI, medicine, and biology.Be part of an environment strongly committed to translating research findings into actionable insights and scalable real-world products. We encourage (and financially support) our postdoctoral fellows to pursue extensive training in entrepreneurship and business management through Stanford’s Graduate School of Business. This position is well suited for candidates interested not only in state-of-the-art academic research, but also in exploring industrial and entrepreneurial career trajectories.Our lab values a friendly and collaborative environment, and we enjoy spending time together outside of work through ski retreats, laser tag, charity events, Christmas parties, and various other get-togethers.As a Stanford postdoctoral scholar, you will receive a highly competitive salary and comprehensive benefits, including best-in-class health and dental insurance. You will also receive priority consideration for Stanford housing and have access to Stanford’s broad range of professional development, learning, and growth resources.Relevant background:MD or PhD, with research experience building and/or applying machine learning models during graduate studies, industry, or postdoctoral work.Excellent publication record.Interest in medicine and biology.Familiarity with modern AI/ML platforms and libraries (e.g., PyTorch and/or TensorFlow), traditional machine learning frameworks (e.g., scikit-learn), and statistical analysis in Python.Preferred, but not required:Familiarity with electronic health record (EHR) data and cohort/outcome definition using EHRs.Experience training foundation models or other large-scale deep learning models, including on multimodal data.Experience in medicine and/or biology, particularly in omics-based analyses.Broad experience across diverse AI/ML concepts, including causal inference.Publications in leading AI/ML, biology, or medicine conferences and journals.Keywords:Machine Learning, Artificial Intelligence, Deep Learning, Foundation Models, Multimodal Learning, Electronic Health Records, Real-World Data, Causal Inference, Precision Medicine, Biology, Omics, Genomics, Proteomics, Metabolomics, Biomarker Discovery, Data Science, BioinformaticsApplication information:To receive full consideration, please apply using the following Google Form: https://docs.google.com/forms/d/e/1FAIpQLSdgPBJi028fNIVrbXrXFhDXRbc0gXeIN8wcHjQKKiObPJDmNA/viewform?usp=sf_linkQuestions can be directed to naghaeep@stanford.eduFor more information please visit: https://nalab.stanford.edu