Role overview
We are looking for a Postdoctoral Researcher to develop generative AI methods for nanoparticle (NP) drug delivery design. You will join the research group of Dr. Sepinoud Azimi, working within the NAP4DIVE project (Horizon Europe), a consortium including AstraZeneca, TU Eindhoven, University of Gothenburg, Chalmers, and FinnAdvance.
Nanoparticle drug delivery is a high-dimensional, multi-objective design problem: formulations consist of multiple interacting components whose therapeutic behaviour changes after administration due to biological interactions (protein corona formation, degradation, payload release). Current AI approaches treat NP design as static property prediction. This project takes a fundamentally different approach: using generative models to propose novel NP formulations and coupling them with explainability methods so that design decisions can be understood, validated, and trusted.
As a postdoc, you will:
- Develop generative AI models (e.g., variational autoencoders, diffusion models, or reinforcement learning-based optimization) for NP formulation design, targeting specific therapeutic outcomes such as blood-brain barrier permeability and tumour accumulation.
- Couple generative models with counterfactual explanation methods, enabling researchers and regulators to understand why a proposed formulation is predicted to work and what minimal design changes would alter therapeutic outcomes.
- Co-supervise doctoral candidates working on related topics, including nanoparticle database curation, molecular dynamics-based transport modelling, and reinforcement learning for treatment optimization.
- Contribute to high-impact publications.
You will work alongside PhD students and interact with experimental partners across the NAP4DIVE consortium. You will have access to the DelftBlue high-performance computing cluster.
This position offers a unique opportunity to shape an emerging field. The group is building toward a long-term research programme on trustworthy AI for personalized nanomedicine, and your contributions will directly feed into this vision.
The intended start date is July–August 2026.
What we're looking for
- PhD in machine learning, artificial intelligence, computational chemistry, computational materials science, or a closely related field.
- Demonstrated expertise in generative models for molecular or materials design, with at least one first-author publication using variational autoencoders, diffusion models, normalizing flows, or reinforcement learning-based design optimization.
- Strong programming skills in Python with experience in PyTorch, JAX, or equivalent deep learning frameworks.
- Ability to work independently, formulate research questions, and drive projects to publication.
- Excellent written and spoken English.
- Experience with drug delivery, nanomedicine, pharmaceutical formulation, or materials informatics.
- Familiarity with explainable AI or counterfactual explanation methods.
- Experience with molecular dynamics data, graph neural networks, or multi-component system modelling.
- Track record of interdisciplinary collaboration.
- You can apply online. We will not process applications sent by email and/or post.
- As part of knowledge security, TU Delft conducts a risk assessment during the recruitment of personnel. We do this, among other things, to prevent the unwanted transfer of sensitive knowledge and technology. The assessment is based on information provided by the candidates themselves, such as their motivation letter and CV, and takes place at the final stages of the selection process. When the outcome of the assessment is negative, the candidate will be informed. The processing of personal data in the context of the risk assessment is carried out on the legal basis of the GDPR: performing a public task in the public interest. You can find more information about this assessment on our website about knowledge security.
- Please do not contact us for unsolicited services.
Faculty/Department: Faculty of Technology, Policy & Management
Salary range: €3546 - €5538
Hours per week: 36-40
FTE: 1,0
Submission is possible until: 20 Apr 2026
ID job: 3150