Postdoc: AI-Driven Drug Design with Closed-Loop DMTA

Universität Basel; Basel; Vor Ort; CHF 90.000 - 110.000; Vollzeit

Zusammenfassung

Universität Basel recruits a fully funded Postdoctoral researcher to advance AI-driven drug design within an international DMTA project. The role focuses on developing ML methods for structure-based and generative design, integrating physicochemical features, and validating approaches in prospective drug-discovery cycles with serine protease inhibitors as a lead case.

The successful candidate will collaborate across computational chemistry, chemistry and biology teams, contribute to

Qualifikationen

• PhD in Computational Chemistry, Cheminformatics, Computer Science, Physics, or a related discipline.
• Strong background in machine learning and deep learning.
• Strong programming skills, particularly in Python.
• Experience in molecular generative AI, cheminformatics and molecular representations, structure-based drug design and protein-ligand modeling.
• A strong publication record in internationally recognized venues (e.g., JCTC, ICML, NeurIPS).
• Fluent English (verbal and written).

Aufgaben

• Develop machine-learning approaches for structure-based and generative molecular design.
• Integrate physicochemical information, including protein-ligand interactions, into generative AI workflows.
• Develop workflows for closed-loop DMTA cycles using experimental data to improve designs.
• Apply and validate approaches prospectively for serine protease inhibitors.
• Collaborate with computational scientists, chemists and biologists within the project consortium.
• Contribute to scientific publications, presentations and project reporting.

Kenntnisse

Machine learning

Deep learning

Python programming

Drug design

Protein-ligand modeling

Ausbildung

PhD in Computational Chemistry

Tools

Python

Molecular modeling

Jobbeschreibung

Universität Basel recruits a fully funded Postdoctoral researcher to advance AI-driven drug design within an international DMTA project. The role focuses on developing ML methods for structure-based and generative design, integrating physicochemical features, and validating approaches in prospective drug-discovery cycles with serine protease inhibitors as a lead case.

The successful candidate will collaborate across computational chemistry, chemistry and biology teams, contribute to