1 day ago Be among the first 25 applicants
As a Multimodal AI Research Scientist at the Biomedical Informatics Group in the Department of Computer Science at ETH Zurich, you will have the opportunity to advance medical research using state-of-the-art machine learning.
Our team has developed a novel machine learning model that enables the generation of virtual spatial transcriptomics data from H&E medical slides using recent pathology foundation models. This approach allows us to generate large multimodal datasets across various tissues and cancer types, providing unique insights into the molecular landscape of cancer biology.
We are currently seeking a Multimodal AI Research Scientist to join our efforts in scaling and training large multimodal foundation models on these unique datasets, with a specific focus on self-supervised learning techniques (e.g., aligning high-resolution imaging, molecular, and text modalities) and generative modeling (e.g., generating realistic tissue images conditioned on text priors).
In particular, you will:
* Join a small, focused team setting the foundations for the development and application of foundation models in biomedical innovation
* Develop and lead the implementation of strategies to align foundation models across different biological modalities, including but not limited to transcriptomics, proteomics, computational histopathology and medical text
* Conduct methodological research for the pre-training and alignment of biological foundation models, targeted at taking advantage of the particular structures and connections between different biological scales
* Evaluate multimodal biological foundation models, up to and including the design of novel evaluation tasks and relevant downstream analyses
* Report and present research findings and developments clearly and efficiently, to both other ML scientists and scientists of different disciplines.
Job requirements:
The successful candidate will be independent, curious, and detail-oriented, and will thrive in a dynamic, fast-paced environment. They will be passionate about the intersection of healthcare/biology and AI. In addition, the candidate should have:
* PhD in Computer Science, Machine Learning, Data Science, Bioinformatics or a related field or an MSc with 2–5 years of relevant experience
* Strong Python programming skills and familiarity with best practices; experience with deep learning frameworks (e.g., PyTorch)
* Strong interest in the intersection of healthcare/biology and AI
* Demonstrated expertise in representation learning, large language models, generative AI, or alignment of foundation models across modalities (e.g., text, image, audio, video)
* Excellent written and oral communication skills
How to apply?
This opportunity is offered through the National Qualification Programme (BNF), which operates throughout Switzerland and brings over 20 years of experience in supporting academics. To be considered for this position, interested candidates should submit their application via the following Google Form (https://forms.gle/7bcgzF3v38581CxTA).
Please note that due to the high volume of applications, only complete submissions will be considered, and only shortlisted candidates will be contacted.
If you encounter any issues, please contact Kalin Nonchev (kalin.nonchev@inf.ethz.ch).
Note: This job offer is for a 6-month internship with no option for extension.
References:
[1] Nonchev, K., Dawo, S., Silina, K., Moch, H., Andani, S., Tumor Profiler Consortium, Koelzer, V.H. and Raetsch, G., 2025. DeepSpot: Leveraging Spatial Context for Enhanced Spatial Transcriptomics Prediction from H&E Images.
[2] Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T.J. and Zou, J., 2023. A visual–language foundation model for pathology image analysis using medical twitter.
[3] Tran, M., Schmidle, P., Guo, R.R., Wagner, S.J., Koch, V., Lupperger, V., Novotny, B., Murphree, D.H., Hardway, H.D., D’Amato, M. and Lefkes, J., 2025. Generating dermatopathology reports from gigapixel whole slide images with HistoGPT.
[4] Yellapragada, S., Graikos, A., Li, Z., Triaridis, K., Belagali, V., Kapse, S., Nandi, T.N., Madduri, R.K., Prasanna, P., Kurc, T. and Gupta, R.R., 2025. PixCell: A generative foundation model for digital histopathology images.
Seniority level
* Seniority level
Internship
Employment type
* Employment type
Internship
Job function
* Job function
Engineering and Information Technology
* Industries
Higher Education
Referrals increase your chances of interviewing at ETH Zürich by 2x
Sign in to set job alerts for “Artificial Intelligence Researcher” roles.
Internship: AI Software stack & Compilation
Delivery Consultant - Machine Learning (GenAI), ProServe EMEA
Delivery Consultant - Machine Learning (GenAI), ProServe EMEA
Computer Vision/Machine Learning Research Scientist (Spatial AI)
Data Scientist - QuantumBlack, AI by McKinsey
Software Engineer, ML & Data Platforms (100%)
Senior Computer Vision ML Engineer - Object Detection + Semantic Segmentation
AI Research Scientist, 3D/4D Generative AI
Software Engineer III, AI/ML, Google Search
Software Engineer III, AI/ML, Creator Reputation
Software Engineer II, Machine Learning, Google Search
Research Scientist, 3D/4D Generative AI for World Generation
Senior ML Performance Engineer – Profiling & Distributed Training
Senior ML Performance Engineer – Profiling & Distributed Training
AI Compilation Researcher (MLIR/Triton/TVM)
Senior Researcher - AI Software Stack & Compilation
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
#J-18808-Ljbffr