Genomic AI Fellows
This program aims to bridge the gap between large-scale genomic data and transformative clinical impact. The fellowship will provide early-career scientists with the resources and environment to develop next-generation Foundation Models (FMs) for the human genome.
The Vision
While DNA sequencing is now a clinical staple, the noncoding “dark matter” of the genome remains largely undeciphered. AI will play a key role in unlocking the sequence-to-function code. As a Genomic AI Fellow, you will collaborate with data generators, computational experts, and geneticists. You will leverage NYGC’s massive, proprietary datasets, including single-cell multiomics and large-scale genetic perturbation datasets, to build models that predict how genetic variation influences cellular behavior and, ultimately, human health.
This is a platform for researchers to lead high-impact projects within a collaborative ecosystem. You will be paired with world-class computational expertise and gain direct access to genomics data and “in-production” multiomics pipelines. Your work will sit at the vanguard of precision medicine, translating the multiomics revolution into actionable biological insights.
Research Opportunities
Genomic AI Fellows are encouraged to explore the frontier of genomic modeling, with access to high-resolution data and high-performance computing to address challenges such as:
- Mapping the Regulatory Landscape: Moving beyond bulk-omics to predict cell-type-specific molecular phenotypes directly from DNA sequence.
- Decoding Distal Regulation: Developing novel architectures that can accurately connect distant regulatory elements to transcriptomic output, capitalizing on genetic perturbations.
- Predicting Clinical Trajectories: Utilizing whole-genome sequencing (WGS) from tens of thousands of cases—including Autism, Schizophrenia, Alzheimer’s, and ALS—to predict disease risk and susceptibility via intermediate molecular effects.
Who You Are
We are seeking “high-risk, high-reward” thinkers who thrive at the intersection of machine learning and biology.
- Academic Background: A Ph.D. in Computer Science, Computational Biology, Genomics, or a related quantitative field.
- AI Sophistication: Deep expertise in modern deep learning, foundation models, and large-scale model training.
- Biological Curiosity: A strong interest in (or experience with) gene regulation, epigenomics, or the genetic basis of complex disease.
- Independence: A track record of leading original research and the ability to navigate complex, multi-modal datasets.
