Postdoctoral Scientist Multimodal

• Develop and evaluate multimodal AI/ML methods, including foundation models, predictive models, and generative approaches, for diverse biological data such as high-content imaging, transcriptomics, proteomics, molecular structures, preclinical and clinical assays, scientific literature, and knowledge bases.
• Design computational approaches that generate biologically meaningful hypotheses, inform experimental design, identify mechanisms of disease, and support target or compound prioritization.
• Partner with biologists, chemists, computational biologists, biostatisticians, AI/ML scientists, and data scientists to translate scientific questions into scalable AI solutions.
• Develop workflows that integrate heterogeneous evidence sources and support rigorous, transparent scientific decision-making.
• Contribute to reusable AI platforms, software tools, and data foundations that enable enterprise-scale biomedical AI applications.
• Develop robust benchmarking strategies, establish strong baselines, and evaluate model generalizability, interpretability, and biological relevance.
• Lead end-to-end research activities, including study design, hands-on coding, model development and evaluation, technical documentation, progress reporting, and communication of findings.
• Document and disseminate research findings internally and externally, including through publications in leading AI, computational biology, and bioinformatics venues.

• Ph.D. in Computational Biology, Bioinformatics, Computer Science, Biomedical Engineering, Applied Mathematics, Statistics, Electrical Engineering, or a related quantitative field.
• Strong expertise in machine learning, deep learning, foundation modeling, or related areas.
• Demonstrated experience developing and evaluating machine learning methods for scientific or biomedical applications.
• Hands-on experience with Python and modern AI/ML frameworks and tools, such as PyTorch, JAX, Hugging Face, Git-based version control, Docker, Kubernetes, or equivalent technologies.
• Working knowledge of molecular and cellular biology, genetics, disease biology, or drug discovery, with the ability to connect computational findings to biological interpretation and experimental context.
• Experience analyzing at least one biomedical modality, such as transcriptomics, proteomics, single-cell omics, high-content imaging, tissue imaging, spatial biology, or other high-dimensional biological data.
• Ability to work effectively in multidisciplinary teams and communicate complex analytical findings to both technical and scientific stakeholders.
• Strong scientific communication skills, with the ability to present complex methods and findings clearly to technical and scientific audiences.

Preferences.

• Experience developing multimodal learning systems that integrate two or more biological data modalities.
• Experience with multimodal foundation models, self-supervised learning, contrastive learning, or generative modeling.
• Experience designing AI agents, multi-agent systems, or agentic workflows that support scientific reasoning, hypothesis generation, or experimental planning.
• Familiarity with retrieval-augmented generation, scientific copilots, or autonomous research systems that compile evidence from biomedical literature, databases, knowledge graphs, and experimental data.
• Experience supporting pharmaceutical R&D activities such as target identification, mechanism of action understanding, biomarker discovery, translational research, compound characterization, or precision medicine.
• Experience developing reproducible research software or contributing to shared AI/ML platforms.