PhD fellowship in Agentic AI and Large Language Models for Global Pathogen Analysis Full-time

PhD Fellowship In Agentic Ai And Foundation Models For Global Pathogen Analysis

We are offering a PhD fellowship in “Agentic AI and Foundation Models for Global Pathogen Analysis” commencing September 1st, 2026, or as soon as possible thereafter.

The Bhatt-Duchene Group is based in the Section for Health Data Science and AI at the University of Copenhagen's Department of Public Health. The group works at the intersection of computer science, mathematics, biology, and epidemiology, developing and applying novel statistical methods and deep learning approaches for global health challenges. The group's research spans disease modelling, genomic analysis, causal inference with machine learning, and deep learning for various health-related domains.

The Global Pathogen Analysis Platform (GPAP) is a new international initiative to strengthen global pandemic preparedness by developing a freely available, AI-powered platform for pathogen genomic analysis. GPAP is supported by the Novo Nordisk Foundation with up to DKK 200 million over six years. The platform will be established with its main hub at DTU's National Food Institute and partner nodes at the University of Copenhagen, Statens Serum Institut, and Imperial College London, together with international collaborators in Europe, Africa, and Asia. The PhD fellow will be part of the wider GPAP research environment. The GPAP consortium brings together expertise in artificial intelligence, bioinformatics, pathogen genomics, epidemiology, public health, and software infrastructure. The project will also interact with GPAP collaborators at DTU, Statens Serum Institut, Imperial College London, and international partner sites.

Project description GPAP will provide scientists and public health authorities worldwide with access to advanced bioinformatics and artificial intelligence tools for detecting, tracking, and analysing infectious diseases. A central aim is to reduce technical barriers to pathogen genomic analysis, particularly for users and institutions in low- and middle-income countries. The PhD project will focus on developing intelligent AI systems, language language models (LLMs), and AI-for-Science approaches that can be integrated into the GPAP platform. The project is expected to combine methodological research with robust software implementation and real-world deployment in a large international research infrastructure.

Relevant research directions include, but are not limited to:

• Agentic AI systems for pathogen genomic analysis, interpretation, and automated scientific reporting.
• Tool-using environments and AI systems that can interact with bioinformatics pipelines, databases, and scientific software.
• Pre, mid, and post-training, adaptation, and evaluation of large language models and foundation models for biological, genomic, and phylogenetic tasks.
• Reliable, reproducible, and auditable AI workflows for infectious disease surveillance and outbreak analysis.
• AI methods that support scientists and public health users while preserving data control, transparency, and responsible use.

The successful candidate will be expected to formulate an independent PhD project within this area in collaboration with the supervisory team.

Principal supervisor is Professor Samir Bhatt, Department of Public Health, Email: samir.bhatt@sund.ku.dk

Co-supervisor is Dr Harrison Bo Hua Zhu, Department of Public Health Email: harrison.zhu@sund.ku.dk

Co-supervisor is Dr Neil Scheidwasser, Department of Public Health Email: neil.clow@sund.ku.dk

Start: 1 September or soon after Duration: 3 years as a PhD student [+ 3 months as research assistant for enrolment, if relevant]

Job description Your key tasks as a PhD student will be to:

• Carry out an independent research project under supervision.
• Develop new AI methods and software systems relevant to GPAP.
• Implement, evaluate, and document research prototypes and platform-facing tools.
• Publish scientific papers in high-quality international venues.
• Complete PhD courses or other equivalent education corresponding to approximately 30 ECTS credits.
• Participate in active research environments, including a stay at another research institution.
• Contribute to teaching, supervision, or other forms of knowledge dissemination related to the PhD project.
• Write and defend a PhD thesis based on the project.

Key criteria for the assessment of applicants Applicants must have qualifications corresponding to a master's degree related to the subject area of the project, e.g. data science, statistics, economics, computer science, computational linguistics, or a related quantitative discipline. Please note that your master's degree must be equivalent to a Danish master's degree (two years). In addition, the following will be considered:

Essential experience and skills:

• A strong academic background in computer science, machine learning, applied statistics or a closely related field.
• Practical experience with AI systems, large language models, agentic AI, or scientific software development, especially in industry or research settings.
• Strong software engineering skills, proficiency in Python programming, experience with Git and modern deep learning frameworks (PyTorch/Jax/TensorFlow)
• Ability to work independently and in collaboration with researchers, engineers, and domain experts.
• Strong motivation to conduct internationally competitive research and translate methods into working software.
• Excellent written and spoken English.

Desirable experience and skills:

• Experience with large language model pre/mid/post-training (e.g. Agentic Reinforcement Learning), evaluation, tool use, agentic harness, or retrieval-augmented systems.
• Internship/full-time experience from research, engineering, or algorithm-development roles in AI-focused companies, technology companies, or research laboratories.
• Experience with robust software engineering, reproducible research, high-performance computing, or cloud-based scientific workflows.
• Experience with development of Triton or CUDA kernels.
• Experience with distributed training and LLM infrastructure (e.g. Ray, TRL, vLLM, Triton, DeepSpeed, Unsloth, VeRL) and MLOps tooling (MLflow, Weights & Biases)
• Publications, open-source contributions, research software, or other documented outputs relevant to the project.
• Experience with AI for Science, computational biology, pathogen genomics, phylogenetics, epidemiology, or bioinformatics workflows.

Place of employment The place of employment is at the Department of Public Health, Faculty of Health and Medical Sciences, University of Copenhagen. We offer creative and stimulating working conditions in dynamic and international research environment. Our research facilities include modern laboratories and high-performance computing infrastructure with GPU clusters for large-scale analyses.

Terms of employment The average weekly working hours are 37 hours per week.

The position is a fixed-term position limited to a period of 3 years.

The employment is conditioned upon the applicant's successful enrolment as a PhD student at the Graduate School at the Faculty of Health and Medical Sciences, University of Copenhagen. This requires submission and acceptance of an application for the specific project formulated by the applicant during an initial three-month employment as a research assistant.

The PhD study must be completed in accordance with The Ministerial Order on the PhD programme (2013) and the Faculty's rules on achieving the degree.

Salary, pension, and terms of employment are in accordance with the agreement between the Ministry of Taxation and The Danish Confederation of Professional Associations on Academics in the State. Depending on seniority, the monthly salary starts at approximately 31,600 DKK / 4,200 EUR plus pension.

Questions For specific information about the PhD fellowship, please contact the principal supervisor.

General information about PhD studies at the Faculty of Health and Medical Sciences is available at the Graduate School's website: https://healthsciences.ku.dk/phd/guidelines/

Application procedure Your application must be submitted electronically by clicking 'Apply now' below. The application must include the following documents in PDF format:

1. Motivated letter of application (max. one page)
2. CV incl. education, experience, language skills and other skills relevant for the position
3. Certified copy of original Master of Science diploma and transcript of records in the original language, including an authorized English translation if issued in other language than English or Danish. If not completed, a certified/signed copy of a recent transcript of records or a written statement from the institution or supervisor is accepted. As a prerequisite for a PhD fellowship employment, your master's degree must be equivalent to a Danish master's degree. We encourage you to read more in the assessment database: https://ufm.dk/en/education/recognition-and-transparency/find-assessments/assessment-database. Please note that we might ask you to obtain an assessment of your education performed by the Ministry of Higher Education and Science