The Zhi Laboratory at Yale University (Department of Biomedical Informatics and Data Science) is seeking a highly motivated bioinformatician or computational biologist (Ph.D.) to join a method-driven research group working at the intersection of computational genomics, clinical artificial intelligence, and imaging genetics. This position offers an exciting opportunity to develop novel algorithms and deep learning methods for large-scale genomic, clinical, and imaging biobank data, with stable multi-year NIH support.
The Zhi Laboratory has a sustained track record of methods development, including the PBWT/GBWT family of haplotype algorithms for biobank-scale identity-by-descent (IBD) detection, the Med-BERT and CovRNN clinical foundation models for electronic health records, and the UDIP framework for unsupervised deep imaging phenotyping and imaging GWAS. The lab is now expanding these programs across pangenome informatics, clinical deployment-oriented AI, and multimodal imaging genetics.
Position Overview
The successful candidate will develop and apply advanced computational and machine learning methods to large-scale genomic, clinical, and imaging datasets, working across one or more of the lab’s core research areas. The position involves close collaboration with lab members and external partners spanning genetics, clinical informatics, and imaging, and offers substantial independence to shape a methodological research direction.
This is an outstanding opportunity for an individual interested in combining computational genomics, deep learning, and biomedical data science to address fundamental questions in human genetics, clinical prediction, and brain/cardiac/retinal imaging.
Open Research Directions
Computational Genomics and Pangenomics
Sustained program in large-scale IBD detection and PBWT-based algorithms (RaPID, RAFFI, FiMAP, ROH analysis, local ancestry inference), now extending into GBWT/RLBWT-based pangenome indexing, efficient pangenome graph construction and query, cross-population haplotype analysis, and next-generation IBD algorithms for million-sample cohorts.
EHR Deep Learning and Clinical AI
Foundation model work building on Med-BERT and CovRNN, including continued pretraining and multi-task fine-tuning for clinical foundation models, deployment-oriented validation and benchmarking, multimodal clinical representation learning, PK-RNN-style trajectory modeling, and biobank-linked genetic discovery.
Imaging Genetics and Neuroimaging GWAS
Development of UDIP, an unsupervised deep imaging phenotype framework, including UDIP-Brain (UK Biobank brain MRI) and UDIP-FA, with current projects in multimodal imaging representation learning, imaging-derived phenotype GWAS, Alzheimer’s disease neuroimaging biomarkers, retinal imaging genetics, and multi-omics integration.
Responsibilities
- Develop computational pipelines and machine learning methods for genomic, clinical, or imaging data analysis.
- Analyze large-scale biobank, EHR, and/or imaging datasets.
- Apply statistical, deep learning, and algorithmic approaches to method development and discovery.
- Integrate multiple data modalities to generate and prioritize findings for validation and publication.
- Collaborate with lab members and external partners on study design and result interpretation.
- Maintain reproducible computational workflows and well-documented analysis pipelines.
- Present research findings at laboratory meetings, scientific conferences, and through peer-reviewed publications.
Qualifications
Candidates should possess:
- Ph.D., completed or expected, in Bioinformatics, Computer Science, Statistics, Computational Biology, Biomedical Informatics, or a related quantitative field.
- Strong programming skills in Python and/or C++.
- Peer-reviewed publication record appropriate for career stage.
- Ability to lead independent research projects while collaborating across disciplines.
Experience with one or more of the following is highly desirable:
- Large-scale genomic, clinical, imaging, or other biomedical data
- Haplotype/IBD algorithms, pangenome graphs, or population genetics
- Deep learning for sequence, EHR, or imaging data
- High-performance and GPU computing environments
Excellent candidates from adjacent quantitative fields are encouraged to apply.
The Research Environment
The Zhi Laboratory is based in the Department of Biomedical Informatics and Data Science at Yale School of Medicine, led by Professor Degui Zhi (FACMI, FAIMBE). The lab provides access to Yale clinical data resources, large genomic cohorts including ADSP and UK Biobank, and high-performance GPU computing, within a collaborative environment spanning Yale School of Medicine and external partner institutions. The lab offers individualized mentoring toward academic faculty careers, industry research positions, and national laboratory paths.
Appointment
This is a full-time postdoctoral position with a start date of Fall 2026 (negotiable), with an initial appointment renewable annually based on satisfactory progress and continued funding. The lab has stable multi-year NIH support, including R01 and U01 awards. Salary is competitive and aligned with NIH NRSA standards, with benefits provided in accordance with Yale University policies. Salary will be commensurate with experience per the OPA policy posted here: Postdoctoral Compensation | Office for Postdoctoral Affairs
Application Instructions
Applicants should send one combined PDF to degui.zhi@yale.edu, with the subject line “Postdoctoral Application - Your Name,” including:
- A cover letter (1-2 pages) describing research interests and fit with the lab.
- A curriculum vitae, including a complete publication list.
- Names and contact information for three references.
Applications will be reviewed on a rolling basis until the positions are filled.
Yale University is an Equal Opportunity/Affirmative Action Employer and encourages applications from individuals of all backgrounds.
Contact: degui.zhi@yale.edu · Zhi Lab, Yale BIDS, 101 College St, New Haven, CT