Location
Singapore
Department
Institute of High Performance Computing
Posted
1 week before
About This Role
A*STAR seeks a Senior Scientist in Computing & Intelligence to adapt open and institutionally approved foundation models for primary-care decision support, specifically addressing hypertension, diabetes, dyslipidaemia, and CKD risk scenarios.
Responsibilities
- Prepare model-ready datasets from clinical vignettes, synthetic cases, and guideline-derived tasks.
- Develop experiments for supervised fine-tuning, reinforcement learning, or preference alignment on GP-oriented clinical tasks.
- Implement evaluation scripts for guideline adherence, safety alerts, and structured output quality.
- Support multimodal longitudinal data modelling to represent patient histories, lab trends, and medications over time.
- Work with clinical collaborators to translate multimorbidity requirements into model tasks, prompts, and acceptance criteria.
- Document experiments, datasets, model cards, limitations, and reproducibility steps for internal review.
Requirements
- PhD Degree in computer science, AI, biomedical informatics, computational science, or data science.
- Hands-on experience with Python and deep-learning frameworks such as PyTorch, Hugging Face Transformers, or vLLM.
- Working knowledge of LLM fine-tuning, prompt engineering, retrieval-augmented generation, and reproducible ML experimentation.
- Ability to process structured and unstructured clinical data safely, including tabular records, notes, medications, and lab values.
- Good understanding of model evaluation, error analysis, data quality control, and responsible AI practices in healthcare.