Computational Postdoc in Machine Learning, Biophysics, and Genomics

Cold Spring Harbor Laboratory
Simons Center for Quantitative Biology
United States New York Cold Spring Harbor


Associate Professor Justin Kinney and Assistant Professor Peter Koo seek a postdoctoral fellow to spearhead a newly formed collaboration between their two labs, the goal of which is to bridge the divide between “black-box” deep neural network models in genomics and mechanistically interpretable biophysical models of gene regulation.

Both the Kinney Lab and Koo Lab are situated in the Simons Center for Quantitative Biology at Cold Spring Harbor Laboratory (CSHL). The Simons Center is a closely knit community of researchers that use machine learning and other quantitative approaches to study diverse topics in genomics, evolution, biophysics, immunology, and neuroscience. CSHL is a world-renowned non-profit research institution that is home to eight Nobel Prize winners and consistently ranks among the world’s top institutions in research impact per scientist. Members of the CSHL community benefit from the vibrant Meetings and Courses Program, which hosts leading conferences in many biological disciplines. The Simons Center sits on CSHL’s beautiful main campus, which is located on the north shore of Long Island and is readily accessible from New York City via the Long Island Rail Road. Please visit for more information.

The Kinney Lab develops experimental, computational, and mathematical approaches for deciphering the biophysical mechanisms of gene regulation. The primary biological goal of their research is to quantitatively understand the mechanisms of alternative mRNA splicing, as well as the effects of splice-modifying drugs for treating human disease. Their experimental work centers on the use of massively parallel reporter assays (MPRAs), a technology that Dr. Kinney and his lab have pioneered and continue to advance. They also develop machine learning approaches, including deep learning strategies, for extracting quantitative models of sequence-function relationships from MPRA datasets and for interpreting these models in terms of underlying biophysical mechanisms. Please visit for more information.

The Koo Lab studies the functional impact of genomic mutations through a computational lens using data-driven machine learning solutions. They are broadly interested in applications for studying gene regulation and protein (dys)function. Their approach develops methods to scientifically interpret high-performing deep learning models to distill the knowledge that these models learn from big, noisy biological sequence datasets. The driving biological goal of Dr. Koo and his lab is to elucidate biological mechanisms that underlie sequence-function relationships, with a broader aim of advancing precision medicine for complex diseases, including cancer. Please visit for more information.


Candidates must have (or soon receive) a PhD in Computational Biology, Biophysics, Bioengineering, or related discipline. Candidates must also have one or more first-author research publications and/or pre-prints in the field of quantitative biology, broadly defined. Candidates should have strong written and oral communication skills, the ability to navigate and synthesize relevant research literature, a working knowledge of Python programming, and a familiarity with mathematical methods in machine learning. Experience with the computational analysis of biological sequence data, public genomic databases, deep learning frameworks (e.g., TensorFlow, PyTorch, or JAX), and statistical mechanics at the undergraduate level is a plus.

Start date

As soon as possible

How to Apply