Novartis Launches AI-Focused Postdoctoral Fellowships in Digital Pathology and Chemical Synthesis Prediction
核心洞察
Novartis Biomedical Research is recruiting postdoctoral fellows for two AI-driven projects in Basel, Switzerland, focused on digital pathology and machine learning for chemical synthesis prediction.
The digital pathology fellowship will develop AI approaches to extract biomarkers from H&E, IHC, multiplex immunofluorescence, and spatial transcriptomics data to support oncology therapeutics.
The chemical synthesis fellowship will build machine learning models, including graph neural networks and transformers, to predict reaction outcomes and accelerate drug discovery.
Novartis Biomedical Research has opened applications for two postdoctoral fellowship positions in Basel, Switzerland, aimed at advancing artificial intelligence and machine learning applications across drug discovery. The fellowships, part of the Novartis Biomedical Research Postdoctoral Fellowship Program, target early-career scientists immediately following their PhD training, with 2026 cohort start dates scheduled for October and November.
AI Innovation Postdoctoral Fellow in Digital Pathology
The digital pathology fellowship, based within the AI & Innovation team of Oncology Data Science at Novartis in Basel, focuses on advancing AI-enabled digital pathology approaches to extract clinically and biologically meaningful insights from complex tissue imaging datasets. These datasets include H&E, immunohistochemistry (IHC), multiplex immunofluorescence, and spatial transcriptomics.
Working closely with pathologists, translational scientists, and drug discovery teams, the fellow will gain exposure to the end-to-end oncology research process, spanning biological hypothesis generation, biomarker discovery, and translational decision-making. A central objective is to identify robust image-derived biomarkers and interpret spatial and cellular patterns in the tumor microenvironment to support next-generation oncology therapeutics.
The role emphasizes work with foundational models, including pre-trained, self-supervised, multi-purpose, and multi-modal models, to advance generative AI applications in drug discovery. Essential requirements include a PhD in a relevant scientific discipline completed prior to the fellowship start date, experience analyzing imaging data such as H&E, IHC, multiplex IF, and spatial transcriptomics, and proficiency in deep learning frameworks such as PyTorch. Prior experience with multi-modal data analysis, including digital pathology, is listed as desirable.
Postdoctoral Fellow in Machine Learning for Chemical Synthesis and Reactivity Prediction
The second fellowship, hosted within Global Discovery Chemistry in Basel, sits at the intersection of artificial intelligence, machine learning, and synthetic chemistry. The project aims to develop next-generation machine learning approaches that predict chemical reaction outcomes, reaction conditions, and molecular reactivity using large-scale proprietary and public reaction datasets.
Leveraging more than two decades of reaction knowledge generated within Novartis, the fellow will investigate how modern AI methods—including graph neural networks, transformer architectures, and foundation models—can improve the efficiency and success rate of chemical synthesis. The research will focus on building predictive models that help chemists design more efficient synthetic routes, identify optimal reaction conditions, and expand access to diverse chemical space.
The fellow will collaborate closely with experts in data science, computational chemistry, medicinal chemistry, and synthesis technology, with opportunities to integrate predictive chemistry models into generative AI workflows and emerging laboratory automation platforms. The research is expected to result in high-impact publications and contribute to accelerating the Design-Make-Test-Analyze cycle in active drug discovery projects.
Key responsibilities include analyzing large-scale chemical reaction datasets, developing and evaluating machine learning models for predicting reaction success, conditions, yield, regioselectivity, and molecular reactivity, and benchmarking state-of-the-art AI approaches against synthesis prediction tasks. Essential requirements include a PhD in Data Science, Computer Science, Machine Learning, Cheminformatics, Computational Chemistry, Chemistry, Pharmaceutical Sciences, or a related quantitative discipline, along with strong programming skills in Python and familiarity with modern machine learning frameworks.
Program Structure and Application Details
Both fellowships are full-time training positions of up to three years in duration. The program is designed to develop the next generation of scientific leaders through rigorous research and immersive learning experiences, including the implementation of AI tools in biomedical research.
Fellows benefit from guidance from accomplished scientific leaders, access to advanced technologies and research capabilities, collaboration across disciplines, and a global community of postdoctoral fellows. A Postdoc Practicum offers personalized experiential learning opportunities to explore new scientific domains and build cross-functional expertise.
Application deadlines differ by position. The chemical synthesis fellowship requires submission of a CV and cover letter by July 15, 2026, with a cohort start date of October 1, 2026. The digital pathology fellowship requires submission by September 10, with a cohort start date of November 1, 2026. Both positions require applicants to be eligible to work in Switzerland, and the program is intended for scientists who graduated in 2026.
Novartis states that its purpose is to "reimagine medicine to improve and extend people's lives," positioning these fellowships as a pathway for fellows to grow as scientists and future leaders while contributing to discoveries that may ultimately benefit patients worldwide.