The role is ideal for a dedicated Data Scientist with up to 5 years of experience who is passionate about applying clinical AI and advanced analytics to improve patient outcomes, optimize healthcare delivery, and support evidence-based decision-making. The Data Scientist will work with diverse datasets including electronic health records (EHR), clinical coding standards, genomics, and public health registries to develop data-driven solutions that impact population health at scale in Singapore.

Key Responsibilities

• Analyze and integrate large-scale healthcare datasets (EHR, claims, genomics, registries, public health surveillance).
• Develop, validate, and deploy predictive and prescriptive models to support clinical decision-making and public health interventions.
• Apply machine learning and natural language processing (NLP) to clinical narratives, biomedical text, and unstructured health data.
• Collaborate with clinicians and public health experts to identify high-impact problems and translate them into technical solutions.
• Conduct data-driven evaluations of health interventions, screening programs, and risk stratification tools.
• Ensure data quality, security, and compliance with ethical AI principles.
• Build visualizations and decision-support tools for clinical and policy stakeholders.
• Contribute to publications and presentations on applied clinical AI and health data science.

Required Qualifications

• Bachelor's or Master's degree in Data Science, Computer Science, or related discipline.
• 2-5 years of experience in data science / applied machine learning - ideally in a health setting.
• Excellent programming skills in Python
• Proficiency with machine learning frameworks (scikit-learn, TensorFlow, PyTorch).
• Experience with healthcare data standards and ontologies (e.g., SNOMED CT, ICD, LOINC, HL7/FHIR).
• Ability to communicate results clearly to clinical and non-technical audiences.

Preferred Skills

• Experience with and / or interest in novel deep learning architectures - e.g., fusion or energy-based models and fine-tuning large language models.
• Exposure to EHR, real-world evidence or clinical trial data.
• Exposure to time-series modeling and risk prediction models.
• Familiarity with cloud platforms (AWS, GCP, Azure) and MLOps best practices.
• Prior experience in multi-disciplinary teams involving clinicians, researchers, and policymakers