Machine Learning Postdoc Jobs in New York (NOW HIRING)

Our immune cell reprogramming team integrates foundational research on immunology and disease biology with AI-modeling to develop engineered cells that harness our own immune system to detect and treat early signs of age-related diseases, like cancer, Alzheimer's, and Parkinson's. These technologies will enable precise, context-dependent therapeutic responses only when and where it is needed. You can learn more about our work here. 

Our work brings together three powerhouse universities - Columbia University, The Rockefeller University, and Yale University - into a single collaborative technology and discovery engine.

Our Vision

• Pursue large scientific challenges that cannot be pursued in conventional environments
• Enable individual investigators to pursue their riskiest and most innovative ideas
• Facilitate research by scientists and clinicians at our home institutions and beyond

We are a team of passionate individuals powered by technology, guided by scientific research, and driven by collaboration, working toward a mission to cure or prevent all disease.

The Laboratory of Immunogenomics at CZ Biohub NY (www.mahatlab.com) studies the non-coding regulatory genome to understand and address immune dysfunction in diseases like cancer, autoimmune disorders, and aging. We focus on enhancers-non-coding, highly cell-type-specific transcriptional regulatory elements-and their role in shaping immune responses.

We develop and utilize genomic technologies, including bulk and single-cell nascent RNA sequencing, genome editing, immune engineering, and CRISPR-based functional screens in patient biopsies, organoid systems, and mouse models. Through computational analysis integrating machine learning and AI, we map enhancer-gene networks and identify disease-driving elements. Our goal is to advanc

We seek a Postdoctoral Fellow to investigate how transcription factors regulate gene expression programs in cancer and how disease-associated mutations in transcription factors disrupt these programs to drive malignant phenotypes. Many cancer-linked alterations affect transcription factor binding, chromatin engagement, and transcriptional output, yet the downstream regulatory mechanisms and disease consequences remain incompletely understood. This project aims to define the molecular functions of transcription factors in normal and diseased states, map how mutations alter chromatin and transcriptional regulation, and utilize machine learning to predict and test novel mutant-TF-specific functions.

Transcription Factor Mechanism Discovery

-   Define how transcription factors control gene expression, chromatin accessibility, and regulatory element activity in cancer-relevant cellular contexts.

-   Map transcription factor occupancy, chromatin state, and nascent transcription using GRO-seq/ PRO-seq, CUT&RUN, ATAC-seq, DNA methylation profiling.

-   Integrate transcription factor binding data with enhancer activity, promoter usage, and transcriptional outputs to identify direct regulatory targets and core gene networks.

-   Apply CRISPR editing to test candidate genes, regulatory elements, and pathways.

Mutation-Driven Regulatory Analysis

-   Determine how cancer-associated mutations in transcription factors alter DNA binding, cofactor recruitment, chromatin remodeling, and transcriptional control.

-   Compare wild-type and mutant transcription factor function across genomic, epigenomic, and transcriptional assays to identify mutation-specific regulatory defects.

-   Characterize the mutated-TF-associated co-factors, transcription factor, chromatin remodeling through protein-protein interactions.

-   Dissect how these changes impact oncogenic pathways, lineage identity, cellular plasticity, and disease progression.

AI/ML-Guided Functional Discovery

-   Collaborate closely with AI/ML scientists to apply protein language models and related computational approaches to transcription factors and their disease-associated variants.

-   Use these models to predict potential novel molecular functions, protein-protein interaction partners, and mutation-associated cellular phenotypes.

-   Design and execute experimental strategies to test model-derived predictions in laboratory settings, using genomic, molecular, and functional assays to validate predicted mechanisms and disease-relevant consequences.

-   Help establish an iterative framework in which computational predictions inform experiments, and experimental results refine downstream modeling and hypothesis generation.

Genomic Library Preparation

-   Lead and optimize genomic library preparation workflows for chromatin and transcription-focused assays, with strong emphasis on GRO-seq/PRO-seq, CUT&RUN, ATAC-seq, DNA methylation assays, and RNA-seq.

-   Generate high-quality sequencing libraries from cell lines, engineered models, and primary samples, ensuring rigorous experimental design, QC, and reproducibility.

-   Support comparative profiling across perturbation conditions, mutant backgrounds, and treatment states to reveal context-specific transcription factor biology.

Molecular and Cell Biology Validation

-   Perform core molecular biology methods, including tissue culture, organoid and patient sample processing, ChIP, gel electrophoresis, cloning, FACS, and ELISA etc., to validate mechanistic hypotheses.

-   Use genome engineering and perturbation approaches, including CRISPR-based editing and CRISPR screening, to test the functional consequences of transcription factor mutations and candidate regulatory dependencies.

-   Validate key findings through orthogonal assays in relevant cellular models.

Pathway Integration and Disease Modeling

-   Identify critical downstream effectors, co-factors, and candidate therapeutic vulnerabilities emerging from mutant transcription factor activity.

-   Contribute to the development of mechanistic frameworks explaining how transcription factor dysfunction gives rise to disease.

Essential 

• PhD in Molecular Biology, Cancer Biology, Genetics, Genomics, or a related field.
  Strong hands-on experience in genomic library preparation, particularly for chromatin and transcription-focused assays such as GRO-seq/PRO-seq, CUT&RUN, ATAC-seq, DNA methylation profiling.
• Expertise in basic molecular biology techniques, mammalian cell culture, engineered cell models, and/or primary samples.
• Experience with functional perturbation methods such as CRISPR editing, CRISPR screening, or other genetic manipulation approaches.
• Demonstrated work and publication in transcription factor biology, gene regulation, epigenomics, or cancer mechanisms, reflecting independent experimental work and mechanistic biological insight.

Preferred

• Familiarity with computational biology methods and genomic data analyses.
• Experience studying transcription factors, chromatin regulators, or gene regulatory mechanisms in cancer or other disease contexts.
• Familiarity with comparing wild-type and mutant protein function using genomic and molecular assays.
• Interest in collaborative, interdisciplinary research at the interface of transcription, epigenetics, and disease biology.

The New York, NY base pay for a new hire in this role is Postdoctoral Fellow = $93,000.00. This position may be eligible to participate in Biohub's discretionary annual performance bonus program. Bonus eligibility and targets are determined in accordance with Biohub's total rewards philosophy and may vary by role.

We're thankful to have an incredible team behind our work. To honor their commitment, we offer a wide range of benefits to support the people who make all we do possible. 

• Provides a generous employer match on employee 401(k) contributions to support planning for the future.
• Paid time off to volunteer at an organization of your choice. 
• Funding for select family-forming benefits. 
• Relocation support for employees who need assistance moving

If you're interested in a role but your previous experience doesn't perfectly align with each qualification in the job description, we still encourage you to apply as you may be the perfect fit for this or another role.

#LI-Onsite