Innovation Postdoctoral Fellow, Data Science & AI Vision Foundation Models for Cellular Imaging in AI Drug Discovery
Novartis
August 22, 2026
On-site
San Diego, CA
Clinical Research and Development
Key Responsibilities:
- Develop vision foundation models for high-content cellular imaging using state-of-the-art self-supervised learning.
- Design robust evaluation protocols to measure generalization to unseen assays, perturbations, cell types, and imaging conditions.
- Curate large-scale public and internal microscopy datasets; establish standards for data quality and reproducibility.
- Extend models to multimodal settings by integrating imaging with other modalities (e.g., compound data) for drug discovery/phenotypic profiling.
- Build scalable, reproducible training and inference pipelines across HPC and cloud; maintain clean, well-documented code.
- Propose innovative modeling/evaluation methods; work independently and collaboratively and publish/present results.
Essential Requirements:
- PhD (or equivalent) in a relevant scientific discipline completed prior to start date (PhD conferred in 2026 only).
- Demonstrated scientific achievement (publications, presentations, patents, or equivalent).
- Strong commitment to learning/innovation/professional development.
- Ability to formulate and drive independent research questions.
- Proficiency in Python and modern deep learning frameworks (PyTorch, TensorFlow, or JAX); hands-on GPU training.
- Experience training on HPC or cloud with reproducible code.
- Working knowledge of vision foundation models (self-supervised learning, vision transformers) with fine-tuning/adaptation.
- Experience designing benchmarking/evaluation protocols; strong written and verbal communication.
Desirable Requirements:
- Pretraining vision foundation models from scratch on large-scale imaging datasets.
- Expertise in high-content/biomedical imaging (e.g., Cell Painting, phenomics, digital pathology) and channel-adaptive/multimodal architectures.
- Distributed training on HPC; reproducible ML pipelines on cloud; MLflow.
Benefits & Compensation:
- Starting salary: $87,000 USD/year; comprehensive benefits (health, life/disability, 401(k) match, time off).
How to Apply:
- Submit CV and cover letter by Aug 21, 2026; describe research interests, career aspirations, and how the program supports long-term development.
- Develop vision foundation models for high-content cellular imaging using state-of-the-art self-supervised learning.
- Design robust evaluation protocols to measure generalization to unseen assays, perturbations, cell types, and imaging conditions.
- Curate large-scale public and internal microscopy datasets; establish standards for data quality and reproducibility.
- Extend models to multimodal settings by integrating imaging with other modalities (e.g., compound data) for drug discovery/phenotypic profiling.
- Build scalable, reproducible training and inference pipelines across HPC and cloud; maintain clean, well-documented code.
- Propose innovative modeling/evaluation methods; work independently and collaboratively and publish/present results.
Essential Requirements:
- PhD (or equivalent) in a relevant scientific discipline completed prior to start date (PhD conferred in 2026 only).
- Demonstrated scientific achievement (publications, presentations, patents, or equivalent).
- Strong commitment to learning/innovation/professional development.
- Ability to formulate and drive independent research questions.
- Proficiency in Python and modern deep learning frameworks (PyTorch, TensorFlow, or JAX); hands-on GPU training.
- Experience training on HPC or cloud with reproducible code.
- Working knowledge of vision foundation models (self-supervised learning, vision transformers) with fine-tuning/adaptation.
- Experience designing benchmarking/evaluation protocols; strong written and verbal communication.
Desirable Requirements:
- Pretraining vision foundation models from scratch on large-scale imaging datasets.
- Expertise in high-content/biomedical imaging (e.g., Cell Painting, phenomics, digital pathology) and channel-adaptive/multimodal architectures.
- Distributed training on HPC; reproducible ML pipelines on cloud; MLflow.
Benefits & Compensation:
- Starting salary: $87,000 USD/year; comprehensive benefits (health, life/disability, 401(k) match, time off).
How to Apply:
- Submit CV and cover letter by Aug 21, 2026; describe research interests, career aspirations, and how the program supports long-term development.