Open Positions

Main Responsibilities

• Designing and implementing advanced deep learning models (graph neural networks and transformer-based language models) in a multi-task framework to jointly predict drug safety, efficacy, and operational risks
• Working with a unique and integrative open benchmark dataset constructed by leveraging large-scale data from open clinical trial registries and results
• Engaging in interdisciplinary collaboration with clinicians and pharmacologists to ensure the derived insights are actionable for optimizing trial design and patient recruitment
• Conduct research in machine learning, with a particular focus on deep learning and multimodal health data analysis
• Develop models based on graph neural networks and large language models
• Collaborate within interdisciplinary teams

Required Qualifications

• Master's degree in Computer Science, Statistics, Engineering, Bioinformatics, or a related computational field
• Solid experience in machine learning and deep learning methodologies
• Specialized focus on graph neural networks and/or transformer-based language models
• Proficiency in programming languages such as Python
• Experience with health data, clinical trial structures, and biostatistics is highly desirable

Supervision

Main Responsibilities

• Lead the development of robust, scalable multi-model/multi-agent deep learning architecture (graph neural networks and transformer-based language models) to perform multi-task prediction of safety, efficacy, and operational risks
• Integrate diverse data modalities (molecular structure, free text, hierarchical data) to build a unique open benchmark dataset
• Demonstrate the generalizability of the developed models across different clinical domains
• Drive prospective evaluation of models on ongoing clinical trials
• Coordinate methodological comparison between the AI framework and Physiologically-Based Pharmacokinetic (PBPK) simulations for drug-drug interaction prediction
• The position may also involve supervising PhD students and Master's students
• The position may also involve offering specialized seminars and contribute to teaching activities

Required Qualifications

• has recently graduated with a PhD in areas such as Computer Science, Biomedical Engineering, Electrical Engineering, Physics, Statistics, or similar STEM fields
• Expert knowledge and practical experience in modern deep learning methodologies, including model design, training, and evaluation for complex, imbalanced health datasets
• Demonstrated proficiency with Natural Language Processing (NLP), Language Models (LMs), and/or Graph Neural Networks (GNNs) relevant to analyzing clinical trial protocols and rich textual health data
• strong, relevant publication record demonstrating the ability to conduct and disseminate high-impact research
• Excellent programming and software engineering skills for developing and deploying open-source, scalable machine learning models
• Experience in biostatistics, clinical data analysis, and/or computational toxicology, particularly with Physiologically-Based Pharmacokinetic (PBPK) modeling or similar drug simulation techniques, is a significant advantage

Supervision