Data Harmonization Analyst

NYU Langone Health • New York, NY

2d • $84,578 - $126,992

About The Position

We have an exciting opportunity to join our team as a Data Science Analyst/Engineer. As part of the Complement-ARIE program, the NYU-Sage New Approach Methodologies (NAMs) Data Hub and Coordinating Center will create a controlled access platform for researchers to share and analyze data resulting from NAMs approaches. The program will build tools to standardize and harmonize NAMs data, store it securely, and provide researchers with powerful analytical and visualization tools. The successful candidate will support implementation of integrated standards tailored for NAMs data. This position focuses on analyzing source data structures, developing source-to-target mapping specifications, authoring ETL functional requirements and data quality assurance frameworks, and ensuring that harmonization workflows are well-defined, reproducible, and aligned with FAIR data principles. The role is analytical and specification-oriented: the Data Analyst designs and documents the logic that guides implementation, rather than executing engineering tasks directly.

Requirements

• Masters degree in a quantitative discipline (Biomedical Informatics, Computer Science, Machine Learning, Applied Statistics, Mathematics or similar field)
• 3 years of experience in machine learning/data science
• Proficiency in at least one programming language (Python, R) and machine learning tools (scikitlearn, R)
• Knowledge of predictive modeling and machine learning concepts, including design, development, evaluation, deployment and scaling to large datasets
• Familiarity with computing models for big data Hadoop / MapReduce, Spark etc.
• Knowledge of databases (Relational / SQL, NOSQL MongoDB etc.)
• Good grasp of software engineering principles.
• Experience in integrating modern software architectures.
• Knowledge and some experience in operational aspects of software development and deployment, including automation, testing, virtualization and container technology
• Knowledge of clinical and operational aspects of healthcare delivery.
• Excellent written and oral communication skills for a variety of audiences
• Qualified candidates must be able to effectively communicate with all levels of the organization.

Nice To Haves

• Experience with OMOP Common Data Model or other biomedical research CDMs
• Experience with programming languages (Python, JAVA, R)
• Familiarity with healthcare or life sciences data standards (UMLS, SNOMED-CT, LOINC), or sequencing data standards (FASTQ, BAM, VCF), etc.
• Knowledge of FAIR data principles and metadata standards
• Familiarity with NAMs methodologies or preclinical research data
• Experience with federated data networks or distributed query systems
• Familiarity with AI/ML tools applied to terminology matching, automated mapping recommendations, or data quality assessment

Responsibilities

• Analyze source NAMs datasets (such as transcriptomics, proteomics, microscopy, imaging, electrophysiology, etc.) to characterize data structure, content, and quality prior to harmonization
• Develop detailed source-to-CDM mapping specifications, including transformation rules, value set crosswalks, and handling of edge cases
• Author functional ETL requirements and data flow documentation to guide pipeline development by engineering staff
• Design data quality assurance (QA) frameworks and acceptance criteria for NAMs datasets, including completeness, conformance, and plausibility checks
• Evaluate and document terminology alignment across existing Vocabularies, Metadata requirements, and source ontologies
• Conduct mapping gap analyses and propose remediation strategies for non-standard or missing terminology coverage
• Collaborate with the Lead Metadata and Standards Specialist to ensure mapping outputs align with metadata standards
• Produce and maintain clear analytical documentation: data dictionaries, mapping catalogs, QA specification sheets, and implementation guide
• Support onboarding of new data contributors by reviewing their data structures and advising on harmonization pathways
• Participate in data quality review cycles, analyze QA outputs, and document findings and recommended remediation steps

Benefits

• financial security benefits
• a generous time-off program
• employee resources groups for peer support
• holistic employee wellness program, which focuses on seven key areas of well-being: physical, mental, nutritional, sleep, social, financial, and preventive care

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level