The project focuses on development of machine learning, deep learning and artificial intelligence algorithms for applications in digital health. The candidate will develop reproducible and scalable pipelines for (a) systematic preparation of real-world datasets from clinical collaborators, and (b) proof-of-concept evaluations of new tools for digital health applications.
Expected skills include one or more of the below:
- Understanding of data preparation and visualization procedures for structured and unstructured clinical data including knowledge extraction and feature engineering.
- Understanding of text normalization, denoising, topic classification, semantic modeling, ontology structuring, and/or unsupervised clustering for visualizing unstructured and noisy textual data
- Systems engineering background and solid understanding of enterprise and personal health systems/applications.
- Capability to develop prototype systems for proof-of-concept evaluation and demonstration of new machine learning/deep learning tools with a view to translational research and clinical deployment.
The position entails working in a multi-disciplinary machine learning and deep learning team in close collaboration with clinicians, nurses, as well as other leading academic and industry partners on impactful projects that have the potential to transform patient-care and deliver improved health outcomes.
- Minimum Bachelor Degree in computer science, computer engineering, electrical engineering, mathematics, statistics, software engineering, data science or related fields
- Expertise in one or more of the following areas: data mining, database management, software engineering, systems development, machine learning, deep learning, predictive analytics, biomedical informatics, healthcare data analytics, knowledge extraction and feature engineering, time series/text analysis or recommendation systems
- Experience in professional capacity or clinical environments is a plus
- Strong programming and software engineering skillsets
- Strong knowledge on database management, data analysis, feature engineering and preprocessing of time series data
- Proficient in Python, R
- Languages: Node.js, C++ or Java
- Familiarity with data preprocessing, data science and data visualization tools (e.g., SAS, Tableau, Knime, WEKA, Jupyter notebooks, deep learning, machine learning and visualization libraries)
- Hands on knowledge on data analytics/machine learning/data mining, and experiences in solving real-world data science problems
- Able to deliver under tight schedule
- Good team player with both research and engineering ethics
- Good interpersonal and communication skills
- Ability to work independently to innovate, and develop pipelines to demonstrate the feasibility of research ideas
- Prior experience with NLP, EMR data, clinical informatics systems and software platforms is a big plus
- Prior experience in dialogue systems, question answering, machine comprehension, recommender systems, information retrieval systems is a plus