Postdoctoral Position in AI-Driven Drug Design at University of Basel

Introduction

The University of Basel is offering a fully funded Postdoctoral Position in AI-Driven Drug Design within its Computational Pharmacy group in Switzerland. The role brings together artificial intelligence, machine learning, molecular modelling, cheminformatics, and prospective drug discovery. It is designed for researchers who want to develop computational methods and then test those methods through real drug-design cycles.

This opportunity stands out because the project links digital predictions with experimental feedback. Instead of treating AI as a standalone prediction tool, the research will build a closed-loop Design–Make–Test–Analyze platform. Therefore, applicants with strong computational skills and an interest in practical drug discovery should examine the position closely.

What Makes This AI-Driven Drug Design Postdoc Different?

Artificial intelligence can generate and rank promising molecules quickly. However, useful drug candidates must satisfy several conditions at once. Researchers also need to consider selectivity, physicochemical properties, possible adverse effects, synthetic accessibility, and experimental results.

The University of Basel project addresses this challenge through an integrated workflow. The planned platform will combine generative AI with very large synthetically accessible chemical spaces, physics-informed molecular representations, off-target prediction, and laboratory feedback.

Moreover, the project will use iterative prospective drug-discovery cycles. The work will include a serine protease from the complement system as a real-world lead-optimization case study. This gives the successful postdoctoral researcher an opportunity to connect methodology development with a concrete scientific application.

Research Areas Covered by the Postdoctoral Position

The successful candidate will contribute mainly to the computational and AI components of the project. Several technical areas are particularly important.

Generative AI and Molecular Design

The researcher will develop and adapt machine-learning methods for structure-based and generative molecular design. This work may involve models that propose new molecular structures while considering useful chemical and biological constraints.

In addition, the researcher will integrate physicochemical information into generative workflows. Protein-ligand interaction features will form part of this effort.

Closed-Loop Drug Discovery

A major feature of the role is the closed-loop DMTA approach. Design–Make–Test–Analyze cycles allow experimental findings to influence subsequent computational design.

For example, measured affinity or selectivity data can help refine the next set of proposed molecules. As a result, computation and experimentation become part of one continuous research process.

Molecular Modelling and Protein-Ligand Interactions

The Computational Pharmacy group works on computational drug discovery, protein-ligand and protein-protein interactions, molecular modelling, and deep-learning methods. Its research also addresses challenges such as protein flexibility, solvation, binding-affinity estimation, and kinetic properties.

That background makes the position particularly relevant for researchers working at the intersection of AI and computational chemistry.

Eligibility for the University of Basel Postdoctoral Position

The vacancy requires a PhD in Computational Chemistry, Cheminformatics, Computer Science, Physics, or a related discipline. Candidates should also demonstrate a strong foundation in machine learning and deep learning.

Strong Python programming skills are specifically required. In addition, applicants should have experience in at least one relevant area, such as:

• • Molecular generative AI

  • Cheminformatics and molecular representations

  • Structure-based drug design

  • Protein-ligand modelling

Experience with molecular modelling and the physicochemical principles behind molecular recognition is highly desirable. The vacancy also asks for a strong publication record in recognised research venues relevant to the candidate’s background.

Furthermore, candidates need fluent written and spoken English. The group also values independence, collaboration, and an interest in prospective drug discovery.

What the University of Basel Offers

The postdoc is a fully funded position within an international Innosuisse research project focused on AI-driven closed-loop drug discovery. The role is full-time, listed at 100%, and available immediately.

The research environment is interdisciplinary. Therefore, the successful researcher will work with computational scientists, chemists, and biologists. The project also involves international and industrial partners.

This structure can be valuable for postdoctoral researchers who want experience beyond computational method development. Direct interaction with experimental and industry-linked teams can also provide a broader view of how AI methods move toward practical drug-discovery applications.

How to Apply for the AI-Driven Drug Design Postdoc

Applicants must submit their materials through the University of Basel online recruiting platform. The vacancy is currently listed as available immediately. The official posting does not state a fixed closing date, so candidates should check the application portal before submitting.

The application requires four main components:

1. 1. A motivation letter of no more than one page.

   2. A CV that includes a publication list.

   3. A PhD certificate or confirmation of expected completion.

      Advertisements

   4. Contact details for at least two academic references.

How to Strengthen Your Application

A strong application should connect your previous research directly to the project’s scientific problems. Do not simply list software or algorithms. Instead, explain what you developed, why you developed it, and what the research achieved.

For instance, a candidate with experience in graph neural networks could highlight a molecular-design project and explain its limitations. Likewise, someone trained in cheminformatics can show how molecular representations improved prediction or virtual screening.

Your motivation letter should also explain why closed-loop drug discovery interests you. A clear connection between your research record and the project’s DMTA framework can make the application more coherent.

Expert Tips for Applicants

First, review your publication list before submission. Put the most relevant computational chemistry, AI, molecular modelling, or drug-design work where reviewers can find it quickly.

Second, quantify your technical contribution where possible. State whether you designed a model, built a workflow, analysed experimental data, or led a software implementation.

Third, demonstrate scientific breadth. This vacancy sits between machine learning and molecular science. Therefore, purely technical descriptions may not fully communicate your suitability.

Finally, avoid making the application too broad. A focused statement about your expertise, research direction, and interest in prospective drug discovery will usually communicate more clearly than a long catalogue of unrelated achievements.

Why AI Drug Design Needs Experimental Feedback

AI-driven drug design is advancing rapidly, but prediction alone does not eliminate scientific uncertainty. A University of Basel research report has highlighted limitations in current AI approaches for protein-ligand prediction, particularly when models encounter unfamiliar molecules or new binding modes.

This context makes the closed-loop structure of the Basel project especially relevant. Experimental observations can challenge computational assumptions and provide information for the next design cycle.

For researchers, this creates an important methodological opportunity. The goal is not simply to build a powerful model. Instead, the goal is to develop computational systems that learn from real experimental outcomes and support better molecular decisions.

Summary Table

Conclusion

The University of Basel postdoctoral position offers a strong research setting for scientists working across AI, computational chemistry, and drug discovery. Its closed-loop DMTA framework connects machine learning with molecular design and experimental validation. The role particularly suits researchers with PhD-level training, strong Python skills, and experience in generative AI, cheminformatics, or protein-ligand modelling. Because the position is available immediately, candidates should prepare their application documents without delay. Review the official University of Basel vacancy and tailor your application around the project’s computational and drug-discovery goals.

Frequently Asked Questions (FAQs)