Posted in General Business 7 days ago.
Location: Gaithersburg, Maryland
This is an exciting time to join our dynamic organization. OPKO Health is a diversified healthcare company that seeks to establish industry-leading positions in large, rapidly growing markets, including pharmaceuticals, diagnostics, and biologics. OPKO's diagnostics business includes BioReference Laboratories, the nation's third-largest and fastest growing clinical laboratory over the last 35 years, which provides diagnostic testing to physician offices, hospitals, and clinics, among others, and GeneDx, a rapidly growing genetics and genomics laboratory that applies cutting edge technologies to make efficient clinical diagnostic testing and interpretation available for individuals with rare and common genetic conditions. Come join our team and become part of something big, by making our patients and customers the highest priority.
GeneDx is seeking aPrincipal Data Scientist
GeneDx is a rapidly growing CAP and CLIA certified diagnostic genetic testing laboratory for molecular genetics. Our historic mission has been to make clinical diagnostic testing available for people with genetic conditions and their families. We apply cutting edge technologies that provide a wide array of molecular genetic diagnostic tests, including whole exome sequencing and next-generation sequencing panels. We specialize in genetic testing for rare hereditary disorders, but also test for common disorders. To learn more about GeneDx, please visit our website at www.genedx.com.
The Data Science group within GeneDx is 40+ colleagues and growing. We aim to diagnose more patients to end their diagnostic odyssey and improve their clinical care. As a Principal Data Scientist, you would be a critical member in leading these efforts. As a principal data scientist, you would work as part of a team to develop models and software for genomic and phenomic data analysis. This role’s focus is on applying machine learning and natural language processing techniques to solve challenging problems in clinical genomics. The successful candidate must be self-motivated and able set priorities.
• Distill healthcare problems into machine-learning projects with data-driven solutions
• Drive new data science applications from the ground up, from exploratory data analysis to production-grade software
• Lead data science initiatives and manage projects
• Develop novel natural language processing (NLP) solutions to complex problems
• Build recommender systems to highlight relationships between patients, genes, and diseases
• Automate new assays by developing machine learning pipelines
• Collaborate with the engineering team to develop large-scale data processing pipelines
• Collaborate internally on software development and/or statistical analysis for scientific research
• Ongoing assessment and incorporation of relevant public and commercial analytical tools and the development of novel methods as needed
• MS or PhD in Bioinformatics, Computer Science or a related field required
• 3+ years relevant professional experience
• Experience leading end-to-end machine learning project implementation.
• Demonstrated expertise in professional software development practices
• Proficiency in Python or another major scripting language
• Working knowledge of command-line Linux, shell scripting, and HPC/cloud computing (SLURM, SGE, AWS, Azure or similar)
• Working knowledge of relational databases (PostgreSQL or similar) preferred
• Experience with Git, SVN or other version control software
• Prior experience with human genetics or healthcare-related field