PostDoc Positions at EPFL on Biological Foundation Models

EPFL - Swiss Federal Institute of Technology Lausanne

Lausanne, Switzerland

General

The Artificial Intelligence in Molecular Medicine (AIMM) Lab, led by Prof. Charlotte Bunne at EPFL, sits at the interface of computer science, artificial intelligence, and biomedical applications. The lab is affiliated with both the School of Computer and Communication Sciences and the School of Life Sciences, as well as the EPFL AI Center.

We are recruiting a postdoctoral researcher with strong expertise in modern AI, in particular the development of generative AI technologies such as diffusion models, flow matching, generative transformers, or related architectures. The position is highly methodological and focuses on developing new generative modeling approaches, scalable training algorithms, and foundation model technologies.

The role is suited for candidates with a strong machine learning background who are excited to advance the state of the art in generative AI. Prior experience with biological or biomedical data is not required. The position comes with dedicated access to the Swiss National Supercomputing Centre and the Swiss AI Initiative, and offers opportunities for collaboration across AI, science, and industry.

Research directions include

• Generative AI: development of diffusion models, flow matching, autoregressive models, normalizing flows, or related generative architectures.
• Foundation model development: novel pretraining objectives, scalable architectures, tokenization, and model adaptation strategies.
• Scalable AI training: distributed training, efficient fine-tuning, evaluation, and deployment on large-scale compute.
• Multimodal learning: representation learning and generative modeling across heterogeneous data modalities.
• AI for scientific discovery: methodological advances with potential applications across biomedical and scientific domains.

We are looking for candidates with

• A PhD in machine learning, computer science, applied mathematics, statistics, physics, engineering, or a closely related field, completed or near completion.
• Demonstrated expertise in generative AI, such as diffusion models, flow matching, normalizing flows, VAEs, generative transformers, or related methods.
• Strong programming skills and experience with modern deep learning frameworks.
• Experience with large-scale model training, distributed training, or substantial compute.
• A strong publication record at top-tier machine learning conferences and/or relevant scientific journals.
• Excellent communication skills and enthusiasm for ambitious, interdisciplinary AI research.