Doctoral Fellow for Multi-Electrode Array Based Mechanistic Neural Modelling
Join IDLab UGent to develop quantitative mechanistic models for in vitro neural networks using Bayesian inference.
Best for:Best for candidates with a strong background in AI, Bayesian inference, and a passion for modelling biological systems.
Overview
The IDLab at Ghent University is seeking a motivated doctoral researcher to advance the field of in vitro neural modelling. This position focuses on creating quantitative mechanistic models that capture biological dynamics in Multi-Electrode Array (MEA) cultures, enabling principled inference from experimental data. The successful candidate will integrate theory, simulation, and data-driven methods to support experimental design and explore novel information-processing paradigms. You will work within a collaborative, interdisciplinary environment at the intersection of neuroscience and artificial intelligence. The role is designed for a 4-year period, leading to a PhD degree.
What you'll do
- Develop and refine mechanistic models for in vitro neural cultures using Bayesian parameter inference.
- Collaborate with experimentalists to design new experiments through model-based analysis and simulation.
- Implement efficient numerical simulations of differential equations to represent biological dynamics.
- Perform parameter estimation and uncertainty quantification on high-dimensional spatial and temporal data.
- Develop efficient data embeddings for raw recordings from multi-electrode array systems.
- Disseminate research findings through high-quality publications in top-tier journals and conferences.
- Complete all requirements and milestones necessary to obtain a doctoral degree.
Requirements
Degree required: Master’s degree in Computer Science Engineering, Electrical Engineering, Biomedical Engineering, Applied Mathematics, or a related field.
Degree offered: PhD
Language: Fluent in English (speaking and writing).
Instruction: English
- Strong background in AI, including machine learning, neural networks, or reinforcement learning.
- Proficiency in dynamic modelling or Bayesian inference techniques.
- Experience in software development using Python, PyTorch, or C/C++.
- Strong analytical and organizational skills.
- Ability to work autonomously and adhere to research project milestones.
- Must hold or be about to hold a relevant Master's degree.
- Must have demonstrated first-class academic performance.
Funding & terms
How to apply
Interested candidates should contact the supervisors via email with the subject line 'Application: MEA-based mechanistic neural modelling'. Applications must be submitted through the official university portal link provided.
- CV
- Cover letter
- Academic transcripts
- Master thesis summary
Contact
Kris Demuynck· Professor
Create a free profile to unlock your personal match score, the full requirements, funding details and how to apply — in English or Persian.