Data Scientist - Healthcare

The Healthcare Data Scientist along with the IT team develops innovative heath analytics system based on machine learning approaches by integrating medical information and genomics data.

Responsibilities and Duties

• Big Data innovative health analytics. Provide health and biological insight based on machine learning approaches in integration of medical information, genomics and behavioural data.
• Apply cloud compute based real time queries of structured and unstructured data. Speed and accuracy optimization.
• Big Data technologies - Hadoop, Spark
• Designing and developing algorithms of data analysis and visualization solutions.
• High throughput data processing, mining and curation, including detailed analysis, standardization and mapping of longitudinal phenotyping data and ontologies.
• Increase internal and external adoption of advanced data analytics solutions and dashboards.
• Identify new research opportunities, and develop innovative technology solutions to address multi-dimensional research questions.
• Familiarity with genomics technologies and analysis methods as well as facility with scripting or automated tools to prepare large data sets

Required Experience, Skills and Qualifications

• Experienced and fluent with statistical programming language R, PRocessing.js, Python, and others for data extraction, analysis and visualization (mandatory)
• Advance degree in data science, statistics, computer science or related fields.
• Exposure to healthcare, genomics and bioinformatics domains and its data types are a plus
• Text Analytics using NLP
• Experience with at least one machine learning platform such as TensorFlow, Caffe, Theano, CUDA, MXNet.
• Experience with the implementation of text mining algorithms on structure and unstructured data.
• Database - NoSQL such as MongoDB, MySQL, PostgreSQL
• Data curation and data integrity
• Strong critical and computational/ analytical skills. Should be familiar with SQL and relational databases. Knowledge of additional databases, RDF, and Linked Data approaches would be a strong advantage.
• Machine learning algorithms and neural networks.
• Fluency in writing APIs
• Solid foundation of data structures, standardization and algorithms development.
• Strong communication and global collaborations skills.
• Peer reviewed publications in the domain of data science and bioinformatics are a plus