Postdoctoral Fellow, Multimodal Modeling
Core
Design and train self-supervised multimodal models to fuse confocal protein imaging, single-cell protein proximity networks, and mass spectrometry-based phosphoproteomics into shared representations for studying inflammation and autoimmunity.
Role type
Postdoctoral Fellow, Multimodal Modeling
Builds
Shared representations for spatiotemporal regulation of proteins and proteoforms
Domain
Computational biology / Multimodal AI / Proteomics
Deliverable
production ML models
Required skills
Deep learning for images, Self-supervised learning, Multimodal modeling, Graph neural networks, Python, PyTorch/JAX/TensorFlow
Preferred skills
Contrastive learning (CLIP), Topology-aware modeling, Proteomics data analysis, Single-cell omics, Microscopy analysis, Immunology
Technologies
PyTorch, JAX, TensorFlow, CLIP
Responsibilities
Design and train self-supervised multimodal models, Work with graph-structured proximity-network data, Leverage existing high-performing imaging models, Develop cross-modal alignment strategies, Present findings and co-author publications