PhD Candidate in Machine Learning for Large-Scale In Vivo Perturbational Omics Data

This PhD position offers an exciting opportunity to join a collaborative research program at the VIB-Center for Inflammation Research, working with the Guilliams and Saelens teams. The project focuses on developing advanced probabilistic deep-learning models to automatically extract biological and statistical knowledge from in vivo perturbational omics data. The research leverages cutting-edge single-cell CRISPR technologies, enabling high-throughput screening of molecular factors in vivo during development and disease. These technologies significantly enhance the speed, scale, and resolution of immune cell pathway analysis, providing a rich dataset for training causal machine learning models and advancing precision medicine. The core challenge addressed in this project is the multidimensional nature of omics data, which includes variables such as time, perturbation, tissue position, cell state, and statistical power. By integrating modern probabilistic modeling techniques, including diffusion and transformer models, the team aims to automate data analysis, opening new avenues for data interpretation and predictive modeling. The ultimate goal is to develop active-learning-based screening methods to comprehensively unravel developmental and disease states. As a PhD candidate, you will be embedded in both experimental and computational teams, benefiting from a unique interdisciplinary environment. This setting provides expertise in deep-learning model development and direct opportunities for biological validation. The collaborative atmosphere has driven many past successes, as evidenced by several high-impact publications. You will have access to state-of-the-art computing infrastructure and be encouraged to participate in experimental work to better understand data generation processes. Eligibility requirements include a Master's degree in software engineering, computer science, data science, bioengineering, bioinformatics, engineering, physics, or a related field. Candidates should have experience in machine learning or computational biology, programming proficiency in Python, excellent communication skills, fluency in English, and a collaborative mindset. Additional experience with Pytorch or JAX deep learning models and single-cell or spatial omics data analysis is a plus. The position offers a competitive salary, full benefits, and a supportive, inclusive research environment committed to diversity and equal opportunity. Applications are accepted online via the VIB application tool, with required documents including a motivation letter, CV, and degree certificates. For further information, prospective applicants may contact Prof. Wouter Saelens or Prof. Martin Guilliams. Application deadline: December 31, 2026.