BACKGROUND

RESPONSIBILITIES

• Testing standard machine learning models (e.g., NMF, LDA, random forest, decision trees)
• Feature engineering (different vectorization methods to accommodate domain-specific data)
• Research, design, and create custom models to handle data with dependent relationships (e.g. ontologies)
• Adapting or developing and validating simulated and real datasets for use in model evaluation
• Enhancing data collection and extraction procedures for relevant data
• Assessing models for bias due to correlated noise
• Performing statistical analyses with traditional and machine learning methods
• Contribute to preparation of research manuscripts, reports, presentations, reviews, and summaries
• Actively participate and present summaries of work progress at group meetings
• Other duties as assigned

REQUIREMENTS

• Master's Degree in Computer Science, Data Science, Biostatistics, Computational Biology, Genetics or related field or three or more years of relevant work experience
• Basic understanding of genetics (e.g. rare/Mendelian vs complex traits, modes of inheritance)
• Ability to communicate clearly in written and oral communications is essential
• Must be comfortable working independently, taking the initiative to explore possible solutions, and doing both as part of a team
• Expertise in common data science toolkits (e.g. Python, scikit-learn)
• Excellence with machine learning techniques, particularly NMF, LDA, and decision trees
• Flexibility to take on additional tasks as necessary to accomplish team goals

PREFERENCES

• Familiarity with genetic mutation nomenclature/concepts and clinical finding terminology
• Experience developing custom probabilistic models and/or experience applying deep learning methods to build context-aware recommender systems

TERMS

LOCALE

HOW TO APPLY

DEADLINE

POLICY