PhD position in the field of Confidential High Performance Computing for AI in Cancer Care 100%

The research group (led by Prof. Florina M. Ciorba) in the Department of Mathematics and Computer Science at the University of Basel (Switzerland) invites applications for a PhD position funded by the SNF Bridge Discovery project “Family Gene Toolkit : A digital service to support genetic care in Europe" (grant number 237643).

The BRIDGE Family Gene Toolkit project unites three applicants : Prof. Maria C. Katapodi (Nursing, University of Basel), Prof. Maria Caiata-Zufferey (Social Sciences and Health Issues, SUPSI), and Prof. Florina M. Ciorba (High Performance Computing, University of Basel), and 14 clinical partners across Switzerland.

The project aims to advance the Family Gene Toolkit (FGT) v2.0, a digital platform that offers reliable information and prepares families concerned with Hereditary Breast and Ovarian Cancer (HBOC) and Lynch Syndrome (LS) for clinical consultation and shared decision-making, while helping clinicians organize long-term care and monitoring. FGT v3.0 will integrate technological advancements with AI to enhance personalization for patients and improve clinical efficacy.

The PhD candidate will build the secure technical foundation for FGT 3.0 : confidential HPC pipelines, scalable training infrastructure, and fine-tuned medical LLMs trained on clinical guidelines, evidence-based datasets, and real-world medical corpora. These models will be rigorously evaluated using established medical and multilingual benchmarks.

The ideal candidate has a background in AI, security, and / or high performance computing, with clear motivation to apply security, privacy-preserving, and efficient computational methods to AI for genetic healthcare.

Start : April 2026 .

Duration : 4 years (48 months).

You will design, develop, and integrate AI-based and privacy-preserving features into FGT v3.0 within a confidential HPC environment, including :

• Train and fine-tune large medical LLMs (70B-scale) on confidential HPC systems.
• Prepare medical datasets (Clinical Guidelines, NCCN, PubMed, MIMIC) for secure LLM t- raining.
• Develop high-performance pipelines for TEE-based model training and inference.
• Benchmark models using standard medical and multilingual evaluation suites.
• Build prototype chatbot and retrieval systems for clinical partners.
• Integrate medical LLMs with multilingual models (Apertus).
• Contribute to robustness and confidential-AI evaluation workflows.

Your tasks also include :

Requirements for the position :

Please click here to add text

Application /