Data Scientist

Job Overview

This role involves crafting and employing computational tools and systems to analyze and interpret biological and other research datasets. The position includes developing algorithms, computational techniques, and conventional statistical methods. The candidate will contribute to experiment design and take a leading role in creating machine learning and statistical models. Tasks also involve developing and managing databases, ensuring data integration, and overseeing computational infrastructure both on the cloud and on-premises.

Core Responsibilities

• Design and maintain computer programs for data extraction, transformation, loading, and preparation for analysis, including managing clinical and research data sources.
• Develop automated data processing pipelines to standardize procedures and improve efficiency.
• Extract relevant data such as imaging, biosignals, and medical records from clinical systems including proprietary datasets.
• Perform comprehensive data quality control.
• Analyze biological and research data with standard software tools including plink2 for sequencing and genetic data management.
• Conduct quality control at multiple levels (sample, variant, genotype) for genetic sequencing and imputation datasets.
• Apply appropriate statistical models such as linear, logistic, and survival analyses.
• Aid in managing research databases, computational resources, and cloud environments as well as software containerization using Docker.
• Support preparation of reports, scientific publications, and data visualizations; undertake bibliographic research and manuscript assistance.
• Maintain code, documentation, and internal workflow descriptions; use version control systems like git; communicate progress and obstacles proactively to leadership.

Qualifications

• Bachelor's degree in biological sciences, computational programming, or related fields or comparable experience.
• At least one year of experience working with medical or health-related data, involving data pipeline development and analysis.
• Practical knowledge of bioinformatics, biostatistics, systems programming, databases, and data security.
• Proficiency in R and/or Python for statistical programming.
• Experience or capability to develop and maintain computational data pipelines handling large-scale datasets.
• Project management, multi-tasking, and the ability to work independently.
• Strong interpersonal, communication, and problem-solving skills.
• Preferred qualifications include advanced degrees (MS or PhD) in relevant scientific or computational disciplines.