The University of Basel is recruiting a Postdoctoral Researcher in AI-Driven Drug Design for a fully funded international Innosuisse project in the Computational Pharmacy group. The 100% position is available immediately and focuses on generative AI, molecular modelling, cheminformatics and closed-loop Design–Make–Test–Analyze drug discovery.
University of Basel AI Drug Design Postdoc 2026 at a Glance
| Position | Postdoctoral Position in AI-Driven Drug Design |
|---|---|
| Institution | University of Basel |
| Research group | Computational Pharmacy |
| Department | Department of Pharmaceutical Sciences |
| Location | Basel, Switzerland |
| Workload | 100% |
| Funding | Fully funded within an international Innosuisse research project |
| Start | Available immediately |
| Duration | Not stated in the official vacancy |
| Salary | Not stated in the official vacancy |
| Deadline | No fixed closing date stated |
| Posted | 25 September 2026 |
The project aims to establish an integrated Design–Make–Test–Analyze platform in which computational predictions are repeatedly tested against experimental results. The successful researcher will work at the intersection of artificial intelligence, computational chemistry and prospective drug discovery.
Research Scope: AI-Driven Closed-Loop Drug Discovery
The central scientific challenge is to move beyond molecular generation based only on predicted affinity. The project integrates several dimensions of drug design at once, including physicochemical properties, selectivity, off-target effects, synthetic accessibility and experimental feedback.
Generative AI and Chemical Space
The postdoctoral researcher will develop and adapt machine-learning approaches for structure-based and generative molecular design. The project uses ultra-large synthetically accessible chemical spaces and physics-informed molecular representations.
Protein–Ligand Modelling
Physicochemical information and protein–ligand interaction features will be incorporated into generative AI workflows. Experience with molecular modelling and the physical principles governing molecular recognition is therefore particularly relevant.
Closed-Loop DMTA
Experimental affinity, selectivity and molecular-property measurements will feed back into subsequent design cycles. The objective is to create computational workflows that improve from prospective experimental results rather than operating as one-off prediction systems.
Serine Protease Lead Optimisation
The developed approaches will be applied prospectively to the design and optimisation of inhibitors targeting a serine protease from the complement system, providing a concrete drug-discovery use case for the methodology.
Key Responsibilities
The official vacancy assigns the successful candidate a central role in the computational and AI components of the project. Responsibilities include:
- developing and adapting machine-learning methods for structure-based and generative molecular design;
- integrating physicochemical and protein–ligand interaction information into generative AI workflows;
- developing computational workflows for closed-loop DMTA cycles;
- using experimental affinity, selectivity and molecular-property data to improve subsequent molecular proposals;
- applying and validating the methods prospectively in serine-protease inhibitor design;
- collaborating with computational scientists, chemists and biologists;
- working with international and industrial project partners; and
- contributing to publications, presentations and project reporting.
Eligibility and Required Skills
| Requirement | Official Vacancy Expectation |
|---|---|
| Doctoral degree | PhD in Computational Chemistry, Cheminformatics, Computer Science, Physics or a related discipline |
| Machine learning | Strong background in machine learning and deep learning |
| Programming | Strong Python programming skills |
| Relevant research area | Experience in at least one of molecular generative AI, cheminformatics / molecular representations, or structure-based drug design / protein–ligand modelling |
| Molecular modelling | Experience and understanding of physicochemical molecular-recognition principles are highly desirable |
| Research output | Strong publication record in internationally recognised, high-quality venues |
| English | Fluent written and spoken English |
| Working style | Highly motivated, independent and collaborative |
Computational Pharmacy Research Environment
The Computational Pharmacy group is led by Prof. Markus A. Lill within the University of Basel’s Department of Pharmaceutical Sciences. Its research combines computational drug-discovery methodology, molecular modelling and modern deep learning.
Current group research addresses protein–ligand and protein–protein interactions, protein flexibility, solvation effects, binding-affinity estimation, kinetics and pharmacokinetic or adverse-effect prediction. The group also works with modern deep-learning architectures including graph neural networks, transformers, normalising flows, diffusion models and score-based neural networks.
This makes the role particularly relevant to applicants who want to connect AI methodology with physical molecular modelling and experimental drug-discovery workflows rather than pursue machine learning as an isolated computational task.
Application Documents
The official University of Basel vacancy requests the following complete application package:
| Document | Official Requirement |
|---|---|
| Motivation letter | Maximum 1 page, highlighting research interests, relevant experience and skills |
| CV | Curriculum vitae including publication list |
| PhD documentation | PhD certificate or confirmation of expected completion |
| Academic references | Contact details for at least two academic references |
How to Apply
- Read the complete University of Basel vacancy and confirm that it remains active.
- Prepare the one-page motivation letter around your most relevant AI, computational chemistry, cheminformatics or drug-design experience.
- Update your CV and publication list to make relevant computational and methodological work easy to identify.
- Prepare your PhD certificate or expected-completion confirmation.
- Provide contact details for at least two academic references.
- Submit the complete application through the University of Basel online recruiting platform.
For scientific questions about the role, the official vacancy identifies Prof. Markus Lill as the contact person.
CareerAidHub Applicant Guidance
The following points are CareerAidHub application guidance and are not additional University of Basel requirements.
- Lead with one technical story: use the motivation letter to connect one or two strong projects directly to molecular generation, molecular representations, protein–ligand modelling or prospective drug discovery.
- Show scientific context, not only ML performance: explain the chemical or biological problem behind the model and how the method improved a real research workflow.
- Make Python evidence concrete: mention software, model implementation, pipelines, reproducible workflows or open-source contributions where applicable.
- Prioritise relevant publications: make computational chemistry, cheminformatics, molecular modelling or high-level machine-learning work visible early in the CV.
- Explain interest in closed-loop science: the role is not only about generating molecules; experimental feedback and iterative DMTA cycles are central to the project.
- Apply promptly: “available immediately” with no fixed deadline means the vacancy may close once a suitable candidate is selected.
Before You Submit
| PhD fit | Computational Chemistry, Cheminformatics, Computer Science, Physics or closely related field |
|---|---|
| ML / DL | Clearly demonstrated in CV and motivation letter |
| Python | Concrete programming evidence included |
| Drug-design relevance | At least one required research area clearly matched |
| Motivation letter | Maximum 1 page |
| References | At least two academic contacts ready |
| Vacancy status | Re-check before final submission |
Frequently Asked Questions
Is the University of Basel AI-driven drug design postdoc still open?
Yes. The official University of Basel jobs portal continues to list the position as open, 100% and available immediately.
Is there an application deadline?
The official vacancy does not state a fixed closing date. Applicants should apply while the posting remains live.
Is the position fully funded?
Yes. The official vacancy describes it as a fully funded postdoctoral position within an international Innosuisse research project.
Which PhD backgrounds are eligible?
The vacancy names Computational Chemistry, Cheminformatics, Computer Science, Physics or a related discipline.
Is Python required?
Yes. Strong Python programming skills are specifically required, alongside a strong machine-learning and deep-learning background.
What research experience is most relevant?
Applicants should have experience in at least one of molecular generative AI, cheminformatics and molecular representations, or structure-based drug design and protein–ligand modelling.
What documents are required?
The application requires a motivation letter of no more than one page, a CV with publication list, PhD certificate or expected-completion confirmation, and contact details for at least two academic references.
Official Sources
| Current status | OPEN |
|---|---|
| Position | Postdoctoral Position in AI-Driven Drug Design |
| Institution | University of Basel |
| Research group | Computational Pharmacy |
| Posted | 25 September 2026 |
| Workload | 100% |
| Availability | Immediately |
| Deadline | No fixed deadline stated |
| Scientific contact | Prof. Markus Lill · markus.lill@unibas.ch |
| Last verified | 1 October 2026 |
CareerAidHub verified the vacancy status, qualifications, required documents, research scope and application route against live University of Basel sources on 1 October 2026. Applicants should use the official vacancy page for the final application and re-check its status immediately before submitting.