A*STAR

Scientist/Senior Scientist, Precision Health, BII

A*STAR
ResearchSingaporeOnsitePosted 6 days ago

About the role

AI summarised

Join the Research Data Integration Group at the Bioinformatics Institute (BII), A*STAR, to drive discovery at the intersection of AI, computational biology, and clinical research. This role focuses on integrating large-scale, multi-modal datasets (multi-omics, imaging, clinical) to build intelligent agentic AI systems that accelerate biological discoveries and advance precision medicine strategies for metabolic diseases.

ResearchOnsiteBioinformatics Institute

Key Responsibilities

  • Develop and implement AI/ML and agentic AI systems to analyze and integrate experimental/multi-omics and clinical datasets related to metabolic diseases.
  • Leverage agentic AI for automated hypothesis generation, exploratory data analysis, and prioritization of candidate mechanisms, biomarkers, and therapeutic targets.
  • Collaborate with biologists and clinicians to refine AI-driven hypotheses into testable biological studies and validations.
  • Build scalable data pipelines for preprocessing, harmonization, and integration of heterogeneous omics and clinical data.
  • Apply and innovate computational methodologies to uncover disease mechanisms.
  • Drive therapeutic target identification, therapeutic strategies development, and patient stratification using machine learning and AI-driven inference.
  • Build databases and interactive dashboards integrating multi-dimensional omics and clinical data with AI insights.
  • Contribute to high-impact scientific publications, grant proposals, and patent filings.

Requirements

  • Ph.D. in Computational Biology, Bioinformatics, Computer Science, Data Science, Systems Biology, or a related field.
  • Strong foundation in AI/ML, including deep learning, ensemble methods, graph-based learning, agentic AI, and explainable AI.
  • Demonstrated experience in multi-omics data integration and analysis (e.g., RNA-seq, WGS, proteomics, GWAS, pheWAS, drug screens).
  • Proficiency in Python and R, with hands-on experience using TensorFlow, PyTorch, or scikit-learn.
  • Understanding of metabolic disease biology and relevant clinical phenotypes.
  • Experience working with large-scale, multi-dimensional datasets from biobanks, cohorts, or clinical trials.
  • Proficiency in Unix/Linux environments and cloud or HPC architecture.
  • Track record of peer-reviewed publications in computational biology, bioinformatics, or AI.