Job Description

We are seeking a motivated Research Associate to join the Division of Biomedical Informatics under Prof Ngiam Kee Yuan.

The successful candidate will work on developing advanced AI models, including large language models (LLMs), transformer-based architectures, and foundation models, for applications in genomics, multi-omics, and biomedical research. The role offers opportunities to work with large-scale biomedical datasets, develop innovative AI tools, and contribute to research publications.

Responsibilities:

• Process and analyse genomic and multi-omics data, including GWAS, transcriptomics, and functional genomics.
• Research, develop, and train deep learning, transformer-based, and foundation models for biomedical applications.
• Develop and fine-tune LLMs for biological data interpretation and scientific reasoning.
• Integrate multimodal biological datasets for AI model training and evaluation.
• Develop computational pipelines for data processing, model training, and validation.
• Collaborate with researchers and software engineers to develop AI applications and prototypes.
• Contribute to research publications, presentations, and grant proposals.

Qualifications

• Bachelor's or Master's degree in Bioinformatics, Computer Science, Artificial Intelligence, Data Science, or a related field.
• Strong programming proficiency in Python and R.
• Experience in bioinformatics, including genomic data processing, transcriptomics, or other omics analyses.
• Experience with deep learning and transformer architectures including PyTorch or Hugging Face Transformers.
• Understanding of LLMs and foundation models, including model architectures, training, or fine-tuning.
• Experience with foundation model pretraining, self-supervised learning, or multimodal learning is a strong advantage.
• Familiarity with GPU computing, cloud platforms, or high-performance computing is an advantage.
• Strong analytical, problem-solving, and independent research skills.
• Excellent written and verbal communication skills, including scientific writing and presentation.