Scientist/ Senior Research Officer, Bioinformatics, IHDP

Agency for Science, Technology and Research (A*STAR); Singapore; On-site; SGD 70,000 - 95,000; Full time

Job summary

A leading research organization in Singapore is seeking a data analytics specialist to support a cardiometabolic health study. The role focuses on data management, analysis, and the application of advanced techniques including Large Language Models. Ideal candidates will hold a PhD in relevant fields and have experience with Electronic Health Records and molecular epidemiology. This position offers the chance to contribute to impactful health research in a dynamic team environment.

Qualifications

• PhD in Chemistry, Bioinformatics, Biomedical Engineering, Data Science, Statistics, Mathematics, or Computer Science.
• Knowledge of genetic and molecular epidemiologic research.
• Experience with Electronic Health Records and observational data.

Responsibilities

• Analyze large datasets of protein or metabolite profiles.
• Manage data processes in a hybrid AWS cloud environment.
• Apply LLM for processing clinical notes and health records.
• Conduct quality control audits for data accuracy.
• Identify patterns and predictive insights for patient risk assessment.

Skills

Advanced statistical methods

Data analytics

Large Language Models (LLM)

Python

R

Education

PhD in related field

MSc in related quantitative field

Job description

The A*STAR Institute for Human Development and Potential (A*STAR IHDP) focuses on research that aims to improve and impact the health and well-being of Singaporeans across the life course.

Job Description

Support the data management and data analytics deliverables for a cardiometabolic health study. The role focuses on data collection, monitoring, and multi-modal data integration, with a specific emphasis on Electronic Health Records (EHR), genetic/molecular epidemiologic research, and the application of Large Language Models (LLM) for data curation and analytics.

Job Responsibilities

• Apply advanced statistical and computational methods to analyze large datasets of protein or metabolite profiles.
• Implementation of effective data management processes across clinical, multi-omics, and wearables data in hybrid AWS cloud environment.
• Apply Large Language Models (LLM) to extract, process, and analyze information from unstructured clinical notes and health records.
• Proactive quality control audits/quality management plans across longitudinal visits to ensure data accuracy, completeness, and proper usage of data management systems.
• Identify patterns, correlations, and predictive insights to assess patient risk stratification and disease progression.

Job Requirements

• PhD in Chemistry, Bioinformatics or Biomedical Engineering or a related field. A MSc or PhD in Data Science, Statistics, Mathematics, Computer Science, Physics or related quantitative field are also welcome to apply.
• Knowledge of genetic and molecular epidemiologic research (e.g., GWAS, polygenic risk scores, molecular data integration).
• Worked with EHR or observational human data (e.g., handling structured/unstructured data).
• Knowledge of or experience with Large Language Models (LLM) (e.g., prompt engineering, fine-tuning, or NLP for healthcare text), probabilistic modelling, transfer learning, programming in Python, R, or other languages.