Postdoctoral Researcher – Machine Learning

Offer Description

Antiviral drugs are used to successfully treat infections such as HIV and HCV, yet for most life‑threatening and neglected infections no such drugs exist, leaving critical gaps in epidemic and pandemic preparedness. Traditional antiviral drug discovery focuses on a small number of known targets, while the biology of viral replication is far more complex and harbors many undiscovered druggable targets. Our aim is to revolutionize antiviral target discovery by uncovering this untapped landscape.

We have developed high‑throughput, multiplex, high‑content multiparametric phenotypic antiviral assays that enable the screening of hundreds of thousands of molecules in our fully automated high‑biosafety screening facility (CAPS‑IT) against multiple viruses.

You will design, develop, and deploy advanced machine‑learning models that exploit the full complexity of imaging data to identify promising molecules for in‑depth virological studies, ultimately creating the first‑of‑its‑kind "Atlas of Druggable Antiviral Targets". Your role will involve close collaboration with a multidisciplinary, international virology team and experts in AI and computational biology.

Key tasks include:

• Developing and optimizing ML‑driven models within our antiviral screening pipeline to unlock the richness of multidimensional data.
• Extracting and interpreting detailed phenotypic fingerprints at whole‑well and single‑cell resolution in virus‑infected cell cultures.
• Using AI models to cluster compounds, infer mechanisms of action, identify unique activity signatures, and integrate toxicity profiles to reduce false positives and guide prioritization.
• Collaborating with downstream validation groups to iteratively refine models and build an adaptive, evolving discovery pipeline.

PhD in machine learning, computer science, bioinformatics, or a related field.

Strong machine‑learning modelling expertise with experience analysing large‑scale data sets.

Experience with cellular imaging data or virology/immunology is a plus.

• Creation and evaluation of machine‑learning models.
• Familiarity with deep‑learning frameworks such as PyTorch or Tensor Flow.
• Data preparation, especially in a bioinformatics context (cleaning, filtering, etc.).
• Data fusion and advanced algorithms (deep learning, generative AI, kernel methods, Bayesian methods).
• Preferred experience with high‑content imaging or cell‑imaging data (e.g., Cell Profiler, CNNs).
• Knowledge of chemo‑informatics and drug discovery.
• Strong statistical skills (batch effects, confounders, experimental design).

Fully funded position with a competitive salary at KU Leuven. Access to cutting‑edge technologies and a broad collaborative network. Initial one‑year contract, potentially extendable based on performance.