Job Description
A research engineer position is available immediately at the Institute for Infocomm Research (I2R), A*STAR, Singapore.
The position will focus on developing data engineering, data mining and machine learning pipelines for applications in digital health and precision medicine.
Candidates should have strong expertise in two or more of the following areas:
1.
Data engineering, data analytics and data visualization
2.
Health informatics
3.
Statistics, probability or related areas in applied mathematics
4.
Artificial intelligence (AI) or machine learning (ML) approaches, as applied to large healthcare datasets
Ideal candidates should also have demonstrated interests or experience in one or more of the following areas:
Analysis of large-scale real-world healthcare datasets (spanning electronic health records, lifestyle, and -omics data)Extract Transform Load (ETL) processes, workflows and pipelines, as applied to large or multimodal health datasetsApplication of the above processes to advanced AI/ML systemsCore responsibilities include (a) exploration, sensemaking and preprocessing of raw disparate healthcare datasets, (b) design and development of data preparation and ETL workflows and pipelines to leverage large multimodal healthcare datasets for AI/ML solutions, (c) development of automated knowledge extraction and feature engineering pipelines, and (d) translation to various downstream AI model development, inference and evaluation tasks.
The position entails working in a highly inter-disciplinary R&D team in close collaboration with experts in machine learning, public health, precision medicine as well as with clinicians, health ecosystem stakeholders, and government entities on ambitious projects that have the potential to transform patient care and deliver improved health outcomes.
Job Requirements
Bachelors/Masters degrees in Computer Science, Statistics, Biomedical Engineering, Biomedical/Health Informatics, Computational/Systems Biology or other Data Science intensive fields.
Candidates should have strong data science, data engineering, and programming abilities, and working experience in two or more of the following areas:1.
Large-scale data exploration, data engineering, data warehousing, and/or databases
2.
Biomedical/healthcare/clinical data preprocessing and analysis
3.
Knowledge extraction and feature engineering
4.
Machine learning methods (including application of state-of-the-art techniques)
Deep interest in biomedical informatics, algorithm development, and experience with relevant healthcare applications highly encouraged.
Ideally 2 years post degree completion.
Experience in healthcare, corporate or application oriented research environments is a plus. Ability to work independently and as part of highly interdisciplinary teamsQuick and independent learner; able to acquire the necessary domain knowledgeGood communication skills (e.g., for presentations and reports) Strong communication and excellent writing skillsRigorous analytical thinking, knowledge of research methodsAgility in dynamic project environments with impact-oriented mindset Strong programming abilities (e.g. Python, Bash, PySpark, R, C/C++, Java, Perl)Experience with data preprocessing, data science, and data visualization tools (e.g., SAS, Tableau, PowerBI, Knime, WEKA, Jupyter notebooks etc)Comfort within cloud-based data engineering and ML environmentsExperience with biomedical informatics/healthcare data analytics, knowledge representation and model development frameworksFamiliarity with ML/DL frameworks (e.g., PyTorch or TensorFlow)Exposure to text analytics, natural language processing, text mining desirableInterest in MLOps/DevOps infrastructure and pipelines for deploying AI/ML solutions for healthcare applications is encouraged.Cross-disciplinary research experience would be advantageous.Motivated applicants with significant domain expertise and strong programming skills who are looking to switch into AI-related fields and committed to building robust and scalable approaches for population-scale healthcare impact will also be considered.