项目介绍

2026年5月14日

Are you passionate about building the AI systems that will power the next generation of cancer immunotherapy? Do you want to push the boundaries of generative protein design, protein language models, and active learning to solve one of the most challenging specificity problems in computational biology? We are looking for a computationally oriented PhD candidate to join an ambitious Novo Nordisk Foundation-funded collaboration between the Digital Biotechnology Lab (Assoc. Prof. Timothy P. Jenkins, DTU Bioengineering) and the T Cells and Cancer group (Prof. Sine Reker Hadrup, DTU Health Technology).

About the position
This is a computational and AI methods-focused PhD. The project centres on building the algorithmic and modelling infrastructure needed to design highly specific de novo protein minibinders (miBds) that target peptide-MHC complexes (pMHC) for use in next-generation CAR-T cell immunotherapy. pMHC complexes present intracellular tumour antigens on the surface of cancer cells and are the natural recognition target for T cells. Our groups recently demonstrated proof-of-concept in Science (2025) that AI-designed miBds can functionally replace T cell receptors in CAR-T cell constructs. The key bottleneck now is specificity: ensuring miBds bind their intended pMHC target with minimal cross-reactivity to unrelated pMHC complexes or off-target proteins. Solving this computationally is the core challenge of this PhD.

You will build and own the computational platform at the heart of this project. This means working across the full generative design stack: running and adapting diffusion-based structure generation models (RFdiffusion, RFdiffusion2, BoltzDesign), applying protein language models (ProteinMPNN, ESM) for sequence design and scoring, and building hallucination and filtering pipelines to identify high-confidence candidates from large in silico libraries. You will develop active learning strategies that route experimental effort intelligently, feeding binding and specificity data from collaborators in Prof. Hadrup’s group back into the design loop to refine subsequent generations of miBds. The successful candidate will be the architect of the computational platform underpinning the entire project.

Responsibilities and qualifications

• Design and generate structurally diverse miBd libraries using diffusion-based structure generation models (RFdiffusion, RFdiffusion2, BoltzDesign) and protein language model-guided sequence design (ProteinMPNN, ESM variants).
• Develop hallucination and multi-stage filtering pipelines to identify high-confidence binder candidates from large in silico libraries, integrating predicted structure quality, interface metrics, and sequence diversity.
• Build active learning strategies to select which candidates to validate experimentally, maximising information gained per design-test cycle.
• Develop and apply fast computational models for in silico cross-reactivity panning across diverse pMHC sequence spaces and proteome-wide off-target interaction screening.
• Integrate experimental binding fingerprint and specificity data from collaborators into model training and refinement loops, iterating predictions with each new dataset.
• Explore emerging protein design paradigms including flow matching, all-atom models, and structure-conditioned language models as the field evolves.
• Publish results in high-impact peer-reviewed journals and present findings at international conferences.
• Contribute to teaching and mentoring activities within the Digital Biotechnology Lab.
• A strong background in deep learning or generative modelling, with demonstrable project or research experience.
• Proficiency in Python and familiarity with at least one deep learning framework (PyTorch, JAX, or similar).
• Excellent analytical skills and comfort working with open-ended, research-stage problems.
• Strong communication skills and a genuinely collaborative approach to interdisciplinary science.
• Hands-on experience with generative protein design tools: diffusion models (RFdiffusion), structure prediction (AlphaFold, Boltz), or protein language models (ESM, ProteinMPNN).
• Experience with active learning, experimental design, or reinforcement learning applied to scientific problems.
• Familiarity with protein structure, sequence representations, or structural bioinformatics.
• Knowledge of immunology or antigen presentation at a conceptual level.
• Experience with high-performance or GPU-accelerated computing workflows.

You must have:

• A strong background in deep learning or generative modelling, with demonstrable project or research experience.
• Proficiency in Python and familiarity with at least one deep learning framework (PyTorch, JAX, or similar).
• Excellent analytical skills and comfort working with open-ended, research-stage problems.
• Strong communication skills and a genuinely collaborative approach to interdisciplinary science.

It would further be beneficial if you have:

• Hands-on experience with generative protein design tools: diffusion models (RFdiffusion), structure prediction (AlphaFold, Boltz), or protein language models (ESM, ProteinMPNN).
• Experience with active learning, experimental design, or reinforcement learning applied to scientific problems.
• Familiarity with protein structure, sequence representations, or structural bioinformatics.
• Knowledge of immunology or antigen presentation at a conceptual level.
• Experience with high-performance or GPU-accelerated computing workflows.

You must have a two-year master’s degree (120 ECTS points) or a similar degree with an academic level equivalent to a two-year master’s degree.

Approval and Enrolment 
The scholarship for the PhD degree is subject to academic approval, and the candidate will be enrolled in one of the general degree programmes at DTU. For information about our enrolment requirements and the general planning of the PhD study programme, please see DTU’s rules for the PhD education. 

Assessment
We will assess candidates primarily on the basis of their academic track record and depth of experience in machine learning, generative modelling, or computational biology. Demonstrated ability to develop and apply AI methods to real scientific problems, and genuine motivation for the specific challenges of this project, will be weighted heavily. Shortlisted candidates will be invited to interview on a rolling basis.

We offer
DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and appointment terms
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 3 years.

Start date will be 1 September 2026, or as soon as possible thereafter.

You can read more about the Digital Biotechnology Lab at www.digital-biotechnology.com and career paths at DTU here.

Further information
Further information may be obtained from Assoc. Prof. Timothy P. Jenkins (tpaje@dtu.dk).

You can read more about the Digital Biotechnology Lab at www.digital-biotechnology.com andDTU Bioengineering at www.bioengineering.dtu.dk 

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU – Moving to Denmark. Furthermore, you have the option of joining our monthly free seminar “PhD relocation to Denmark and startup “Zoom” seminar” for all questions regarding the practical matters of moving to Denmark and working as a PhD at DTU. 

Application procedure 
Your complete online application must be submitted no later than 19 May 2026 (23:59 Danish time).

Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link “Apply now”, fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

• A letter motivating the application (cover letter)
• Curriculum vitae 
• Grade transcripts and BSc/MSc diploma (in English) including official description of grading scale

You may apply prior to ob­tai­ning your master’s degree but cannot begin before having received it.