Principal Engineer, Computational Engineering, Office of DGCMIO (Research)

You will provide technical leadership to architect and evolve SingHealth's data infrastructure for research and innovation. You will spearhead data engineering initiatives, including data cleaning, structuring, and standardisation to improve research data quality and usability while ensuring interoperability, standardisation and readiness of data pipelines for real-world evidence generation and Artificial Intelligence/Machine Learning.

You will be involved in mapping clinical datasets to standardised frameworks such as the OMOP Common Data Model, implementing Natural Language Processing techniques to enhance unstructured data usability for research, and leading the re-identification and linkage of clinical and operational datasets to support multimodal (text, radiology, digital pathology, videos, genomics) and cross-cohort (inter-institutional) studies.

You will develop a cluster-wide de-identification framework using common hashing methodologies to enable seamless data linkage across institutions and research studies.

Job Requirements

• Bachelor’s Degree in Science, Technology, Engineering, or Mathematics related disciplines with at least 7 years of relevant working experience in data engineering
• Experience in healthcare data engineering and familiarity with clinical terminologies is an advantage
• Expertise in big data architecture, ETL pipelines, and IT operations involving complex and/or large-scale data
• A strategic thinker with strong project leadership and stakeholder engagement skills and the ability to translate research needs into data-driven solutions.
• Strong customer service skills, team skills, and the ability to collaborate within cross-functional teams
• Detail-oriented and results-driven, with the ability to perform under pressure in a fast-paced and complex research environment.