Postdoctoral Fellow: AI​/ML in Aging & Regenerative Biology

Postdoctoral Fellow: AI/ML in Aging & Regenerative Biology | UCSF

The Singh Lab at UCSF ((Use the "Apply for this Job" box below).) is recruiting multiple postdoctoral fellows to develop next-generation AI and machine learning approaches for aging, developmental biology, and suspended animation (diapause). Located at the UCSF Parnassus campus
, our lab works at the intersection of high-dimensional data science and mechanistic discovery.

You will design deep learning and generative models integrating cross-species large-scale single-cell and multi-omic datasets to map conserved aging trajectories and predict intervention outcomes. A major focus includes leveraging structure-based models to advance predictive design of macromolecules. While your primary work will be computational, our lab uniquely bridges prediction and validation. You will collaborate closely with team members leveraging the African killifish model system to experimentally track and test ML-driven findings in vivo.

Our lab is affiliated with the UCSF Bakar Aging Research Institute (BARI) and the Bakar Computational Health Sciences Institute (BCHSI), providing exceptional career development and collaboration opportunities spanning AI/ML, genomics, aging biology, and regenerative medicine across UCSF.

• PhD in computer science, bioinformatics, computational biology, biomedical engineering, statistics, or a related field.
• Strong track record of developing or customizing machine learning/deep learning approaches for complex biological data.
• Experience with high-dimensional biological datasets (single-cell, multi-omics, clinical or spatial datasets).
• Proficiency in Python (preferred) and/or R, and experience working in Unix/Linux-based HPC and cloud environments.
• Strong publication record and excellent communication skills.
• Ability to work collaboratively in an interdisciplinary environment.

Direct experience developing or deploying AI models for biomolecular structure prediction or design is highly preferred
, including genome or protein language models, geometric deep learning, docking, or generative approaches (e.g., Alpha Fold, RoseTTAFold, ESM, Diff Dock, RFdiffusion, or related methods).

Apply directly via Linked In or email your CV, a cover letter summarizing your research interests/fit, and contact information for three references to param.singh
. Applications are reviewed on a rolling basis.