PhD Student - Machine Learning Biosystems Engineering

PhD Student - Machine Learning for Biosystems Engineering page is loaded## PhD Student - Machine Learning for Biosystems Engineering locations:
Baseltime type:
Full time posted on:
Posted Todaytime left to apply:
End Date:
February 28, 2026 (28 days left to apply) job requisition :
At Roche you can show up as yourself, embraced for the unique qualities you bring. Our culture encourages personal expression, open dialogue, and genuine connections,  where you are valued, accepted and respected for who you are, allowing you to thrive both personally and professionally. This is how we aim to prevent, stop and cure diseases and ensure everyone has access to healthcare today and for generations to come.

Join Roche, where every voice matters.### ### The Position The ML for Biosystems Engineering group led by Jonas Fleck at the Institute of Human Biology (IHB) in Basel, Switzerland is seeking a PhD student to develop machine learning methods for organoid phenotyping and high-throughput screening. Join our group and contribute to advancing the state of the art in computational methods for complex human model systems and drug discovery.###

The Opportunity You will lead and conduct a research project developing computational methods to address important challenges in organoid engineering and drug discovery. Working in a highly collaborative environment with outstanding computational and experimental scientists, you'll develop and apply state-of-the-art machine learning methods to tackle challenging questions in human biology and disease.

You'll have the chance to work with rich, high-content datasets from complex human model systems, such as large-scale perturbation experiments with multi-modal readouts. In collaboration with experimental scientists at IHB, you will also have the opportunity to shape future experiments, enabling you to develop methods with direct translational impact.

Possible research areas may include:
* Predictive ML methods for high-throughput perturbation screens in organoids.
* Multimodal integration methods and foundational models of imaging and genomics data for comprehensive organoid phenotyping.
* Predictive methods for cell fate engineering.
* Methods for causal and mechanism discovery from high-content perturbation experiments.
* Active learning strategies for iterative experimental design ("lab-in-the-loop").Working in a fast-paced research environment bridging computational innovation and experimental biology, you will contribute to the advancement of next-generation human model systems for drug discovery. You'll publish your work, contribute to open-source tools used by the broader research community, and gain exposure to drug discovery and development processes while developing your skills as a computational researcher.###

Who you are
* You are a Master’s student or recent graduate in computational biology, computer science, machine learning, bioinformatics, or a related technical field.
* You are proficient in Python and familiar with modern ML frameworks such as JAX, PyTorch, or Tensor Flow.
* You are knowledgeable in modern software engineering tools and methodologies, including version control (Git Hub/Git Lab), CI/CD, and software packaging.
* You are grounded in strong fundamentals of linear algebra and statistics, with familiarity in applying modern statistical and machine learning methods to genomics data.
* You are an excellent communicator in English, possessing the ability to explain complex technical concepts clearly to a non-technical audience.
* You are skilled in data visualization and able to communicate complex findings in a clear and impactful manner.
* You are driven to creatively tackle challenging problems in biomedical research and enthusiastic about translating ML methods into real-world applications in collaboration with experimental scientists.### Nice to have:
* Track record of relevant publications or contribution to open-source code bases.
* Experience applying ML methods to biomedical data (genomics, imaging, or other high-dimensional datasets).
* Experience in single-cell genomics data analysis (scRNA-seq, scATAC-seq, and/or multimodal datasets), image analysis…