- Gaithersburg, Maryland, United States
- On-site
- Contract · Mid
- 4+ years
Responsible for designing, developing, and implementing automated scientific data extraction and standardization solutions supporting the National Institute of Standards and Technology (NIST) CHIPS METIS initiative. Develops advanced Python-based pipelines to extract figures, charts, and tables from scientific documents and transform non-standard research data into structured, machine-readable formats.
Responsibilities
- Design and implement automated OCR and document layout analysis pipelines to extract scientific figures, charts, and tables from PDF and Microsoft Word documents.
- Develop algorithms to identify and extract figure captions, axis labels, measurement units, and associated scientific metadata.
- Implement table extraction capabilities that preserve row and column structures, headers, and data relationships.
- Integrate extracted metadata with established controlled vocabularies and ontologies within the Controlled Vocabulary Curation System (CVCS).
- Develop and enhance user interfaces that enable scientific domain experts to validate extracted content and correct OCR errors.
Requirements
- Bachelor's degree (four-year) in Computer Science, Data Engineering, or a related field.