PhD Position in Statistics with a focus on Statistical Machine Learning for Self-Driving Microscopy
100%
Joint project between – Pertz Lab (Institute of Cell Biology) & D. Ginsbourger's Group (Institute of Mathematical Statistics & Actuarial Science)
We are seeking highly qualified, motivated and creative candidates wishing to join a collaborative project at the interface of statistical machine learning and live-cell biology.
The PhD in statistics will be co-supervised by Prof. David Ginsbourger (Statistics) and
Prof. Olivier Pertz (Cell Biology), and the student will be equally embedded in both research environments.
Your Environment
This project provides a rare opportunity to see statistical machine learning models come alive, guiding live experiments. The recruited PhD student will evolve between both groups and become fluent in communicating across disciplines, a major career asset.
Project Overview
Cells sense, integrate, and respond to dynamic stimuli through complex signaling networks. The Pertz Lab has developed powerful optogenetic tools and fluorescent biosensors that allow direct perturbation and measurement of these networks using light. D. Ginsbourger's group is Internationally recognized in Gaussian process modeling, Bayesian optimal design, and statistical data science for the sciences. Together, we aim to create autonomous “self-driving” microscopes that:
Key methods will include Gaussian Processes (heteroscedastic & multivariate), Operator-valued and deep kernels, Active learning / Bayesian experimental design, Physics-informed machine learning, Closed-loop control of biological systems.
There may be a possibility to complement base PhD funding by taking up teaching and consulting duties. The funding is secured for up to four years with the starting date of September 1st 2025 or as can be arranged by mutual agreement.
- build statistical models of biological dynamics in real time
- predict the most informative next experiment
- execute it automatically on living cells
Key methods will include Gaussian Processes (heteroscedastic & multivariate), Operator-valued and deep kernels, Active learning / Bayesian experimental design, Physics-informed machine learning, Closed-loop control of biological systems.
There may be a possibility to complement base PhD funding by taking up teaching and consulting duties. The funding is secured for up to four years with the starting date of September 1st 2025 or as can be arranged by mutual agreement.
Your Profile
The ideal candidate will have recently earned or be about to finish their master's degree in statistics or neighboring subjects with a strong mathematical component, a genuine interest in statistical data science and applications thereof, a taste for both theoretical investigations and numerical experiments, solid programming skills (Python, R, Julia, Matlab...), motivation to work closely with experimental researchers, and, of course, curiosity about biological systems - no prior wet-lab experience needed!
Application
Please submit your application only electronically in a single PDF with the following documents:
in one email to both project group leaders:
Please do not apply via the application button.
- short motivation letter (max. 1 page)
- CV including month/year
- BSc and MSc transcripts (in one of Switzerland's official languages, or English) of scores
- Contact information for two references
- Any other relevant document
in one email to both project group leaders:
olivier.pertz@unibe.ch
david.ginsbourger@unibe.ch
Please do not apply via the application button.
Applications will be reviewed on a rolling basis until the position is filled.
