Job

• Construction of a curated, quantum- and AI-ready multimodal radiogenomics data foundation (imaging, genomic, and clinical datasets).


• Quantum state encoding of radiomic, genomic, and clinical features, combined with generative AI models (e.g., diffusion models, transformer-based architectures, quantum GANs) for synthetic data augmentation, missing-modality imputation, and cross-modal translation.


• Quantum-native and generative AI-driven learning and inference, including measurement-driven prediction and uncertainty characterization for clinical decision support (e.g., mutation status, therapy response). Expected Outcomes:


• Publications: Minimum of 2 peer-reviewed publications in high-impact quantum computing/biomedical informatics journals, covering
  
  
  
  • the quantum-ready multimodal dataset and preprocessing pipeline
  
  
  • quantum encoding and entanglement-based interaction modeling
  
  
  • the end-to-end quantum-native inference pipeline with uncertainty analysis.
  
  
  
  


• Patents: At least 1 patent filings anticipated — one covering the novel quantum feature-encoding/entanglement scheme for multimodal biomedical data, and one covering the quantum measurement-based inference and confidence-estimation methodology for clinical prediction tasks.

Key Responsibilities:

• Conduct and lead high-impact research in quantum-native/hybrid learning frameworks for radiogenomics, spanning quantum data encoding, cross-modal interaction modeling, and measurement-driven inference.


• Develop and standardize protocols for curating, harmonizing, and quantum-encoding multimodal datasets (imaging, genomic, and clinical data).


• Supervise and guide undergraduate and doctoral researchers working on quantum circuit design, data pipeline development, and clinical validation Tasks