HPI is recognized as one of the leading university institutes for computer science (www.hpi.de). Our goal is to strengthen Europe's digital sovereignty with excellent research and practice-oriented teaching in computer science. At HPI, we are convinced that excellence is created when knowledge from different disciplines is collaboratively combined to create responsible and pioneering solutions for the future.
In our research clusters "Systems," "Data and AI," "Foundations," "Digital Health," "Security," and "Business and Society" researchers from various disciplines work together on topics relevant to solving the challenges facing society. The Digital Engineering Faculty of the University of Potsdam and HPI offers a computer science engineering degree program that is unique in Germany. 

In the course of its strong growth, the Hasso Plattner Institute is looking for the earliest possible start date for a

 PhD Candidate (f/m/x) - Post-Training, Reasoning, and Multimodal Health AI 

The position is temporary (3 years, with possibility of extension) and full-time, starting from July 2026. 

The Chair of Human-Centred Transformative AI at HPI develops AI that is small enough to be sovereign, capable enough to be useful, and trustworthy enough to be deployed in high-stakes health decisions. Our core research spans efficient reasoning architectures, interpretability and data attribution, and differential privacy - all aimed at enabling compact, private, and auditable medical AI. We work with leading clinical and research partners including Mount Sinai Health System in New York.

Your future tasks

• Develop efficient post-training methods - including fine-tuning, LoRAs, and (private) adaptation techniques - that enable compact pre-trained models to achieve strong performance on medical reasoning tasks including with formal privacy guarantees
• Investigate and improve the reasoning capabilities of sub-4B parameter models through post-training interventions: instruction tuning, reinforcement learning from human/AI feedback, chain-of-thought distillation, and related techniques
• Design and evaluate multimodal integration strategies for medical data - combining clinical text, imaging (radiology, pathology), genomics, and structured health records within compact model architectures
• Build and curate medical reasoning benchmarks and evaluation protocols that reflect clinically meaningful capabilities, in collaboration with our clinical partners
• Contribute to the group’s differentially private synthetic data pipeline for data-scarce medical domains
• Publish at top-tier venues (NeurIPS, ICML, ICLR, AAAI, MICCAI) and contribute to the group’s collaborative research programme

Your skills

• Master’s degree (or equivalent) in computer science, machine learning, mathematics, or a closely related field
• Strong background in at least one of: post-training methods (fine-tuning, RLHF, instruction tuning), multimodal learning, data attribution, or reasoning in language models
• Familiarity with differential privacy concepts or willingness to engage deeply with privacy-preserving machine learning
• Experience with medical or biomedical data (imaging, NLP on clinical text, genomics) is a strong plus
• Proficiency in Python and modern deep learning frameworks (PyTorch preferred)
• Strong publication record or demonstrated research potential (e.g. outstanding thesis)
• Fluent English; German is welcome but not required

What we offer

• A first-class, active and inspiring research environment at the intersection of efficient AI, privacy, and health
• The opportunity to produce research that truly has an impact — our group’s mission is to build AI that empowers patients
• Collaboration with leading international partners including Mount Sinai Health System (New York) and HPI’s Digital Health Cluster
• Regular team events and workshops 
• For problems of any kind (including those in your private life), you can use our external employee counseling service free of charge
• Attractive employee offers (corporate benefits)
• Company-subsidized public transportation ticket / "Deutschlandticket"
• Possibility to work remotely (up to 2 days a week)
• 30 days of vacation plus two additional days off on Christmas Eve and New Year's Eve
• Numerous sports facilities (tennis and basketball courts, beach volleyball court, calisthenics park, and participation in running events)
• Workplace on the HPI campus in Potsdam-Babelsberg (Griebnitzsee S-Bahn station), with fast transportation connections to Berlin

We look forward to receiving your application, including motivation letter, CV, relevant transcripts or degree certificates, a sample of your scientific work (e.g. thesis, excerpt or publication), reference letters (if available), as well as your salary requirements by April 30, 2026. The expected start date is July, 2026, and interviews will be conducted in May 2026.

Please apply exclusively via our career page.

Contact HR Recruiting
nicola.mertens@hpi.de

Contact Research Group
office-kaissis@hpi.de

Hasso-Plattner-Institut für Digital Engineering gGmbH
Prof.-Dr.-Helmert-Str. 2-3
14482 Potsdam