A*STAR

Research Officer (Large Language Models & Data Engineering), A*STAR BII

A*STAR
ResearchSingaporeOnsitePosted 1 month ago

About the role

The Research Officer will lead the integration and fine‑tuning of large language models for processing unstructured clinical text to support antibiotic stewardship in lower respiratory tract infections. The role involves building data pipelines, RAG and knowledge‑graph components, evaluating model performance, and collaborating with interdisciplinary researchers to deliver explainable AI recommendations.

ResearchOnsiteBioinformatics Institute

Key Responsibilities

  • Contribute to LLM development for clinical and biomedical text processing
  • Fine‑tune and train LLMs (e.g., LLaMA, Mistral, Phi, GPT family) using supervised and instruction‑based datasets
  • Design and implement pipelines for data cleaning, preprocessing, and tokenisation of large‑scale corpora
  • Integrate retrieval‑augmented generation (RAG) and knowledge‑graph components for domain adaptation
  • Evaluate model performance using BLEU, ROUGE, BERTScore, and factual consistency metrics
  • Develop optimized PEFT/LoRA/QLoRA fine‑tuning frameworks for efficient GPU‑cluster training

Requirements

  • Master's or Bachelor's degree in Computer Science, Data Science, AI, Computational Linguistics or related field
  • Strong experience in NLP, transformer‑based models, and