Clinical Informatics Services Data… at Medidata… · New Jersey

Summary: Medidata Solutions is a leader in powering smarter treatments and healthier people through innovative digital solutions for clinical trials. The Clinical Informatics Services Data Engineer Intern will develop and maintain digital health data pipelines, implement ETL processes, and collaborate with data scientists to define healthcare data ingestion solutions. Responsibilities: - Develop and maintain digital health data pipelines - Implement ETL processes focusing on efficiency and reliability - Work together with the data scientists to help define healthcare data ingestion solutions - Learn new technologies and their optimal application to our context - Be an active interface with other R&D Groups - Help to find the best dataset for specific business projects - Communicate concisely using the most appropriate approach for each different stakeholder - Prepare the data for machine learning, feature selection, evaluate the performance of algorithms with resampling, machine learning algorithm performance metrics, familiar with classification and regression, automate machine learning workflows with algorithms, improve performance with Algorithm tuning and ensembles - Understand the data with descriptive statistics - Understand the data with visualizations - Work with raw or aggregated data (statistics) for development and innovation purposes - Properly anonymize data sets that can be extracted and used in variety of use-cases - Integrate data sets (Building the capabilities of embedding real-world data, synthetic controls into clinical development programs) - Utilize multiple data collection modalities such as eCOA, Medication adherence devices, Wearable, Sensors - Familiar with data handling strategies to: address illogical data directly from the source and how to 'disqualify and/or flag' implausible data, identify and evaluate: data outliers, data trends such as the range, consistency, and data variability within and across sites, systematic or significant errors in data collection, potential data manipulation or data integrity problems - Pattern recognition & process optimization (New data sciences methods to plan, predict and manage the risks in clinical trials based on both RCT & RWD) - Drive the development of tools extracting meaningful insights to detect potentially unreliable data threatening the validity of the trial results Required Qualifications: - Currently pursuing a Bachelor's or Master's degree in computer science, mathematics, engineering, or statistics - Experience with Python, data modeling, wrangling and data visualization - Familiarity with data analytics and analysis techniques - Familiarity with AWS with a specific focus on data-oriented services - Understand the implications of data context, quality, source, amount, and workflow - Advanced analytical and technical skills to interrogate and mine high volumes of data from a variety of data sources Required Skills: Python, Data modeling, Data visualization Important Skills: AWS, Data analytics Nice-to-Have Skills: Advanced analytical skills, Technical skills