Repository Metadata Librarian: AI & Data Quality (Hybrid)

Computercraft-Corporation; Bethesda (MD); Hybrid; USD 70,000 - 85,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Disability insurance

Life insurance

401(k) plan with matching

Paid leave 128 hours/year for first 3 

11 paid holidays

Work-life balance

Job summary

Computercraft provides a challenging role to support the National Library of Medicine (NLM) at NIH in Bethesda, Maryland. The Repository Services and Metadata Librarian will focus on technical information management, data analysis, quality control, and related tasks for the Digital Repository.

The role requires a Bachelor’s degree and two years’ experience with digital repositories and metadata, plus strong Solr querying and data-analysis skills.

Qualifications

• Bachelor's degree in a relevant field.
• Two years of experience with digital repositories, digital libraries, library systems, archives, or large metadata collections.
• Strong data analysis, data quality, and metadata cleanup skills.
• Ability to construct and interpret Solr queries and to analyze search and index data.
• Working knowledge of structured metadata formats, including XML, JSON, MODS, MARC-derived metadata, or similar schemas.
• Experience with spreadsheets, query tools, text-processing tools, or lightweight scripting for data analysis; programming expertise is not required.
• Strong analytical, problem-solving, communication, and documentation skills.
• Ability to obtain Public Trust clearance.

Responsibilities

• Analyzing repository metadata and content to identify and correct incomplete, inconsistent, duplicate, obsolete, or malformed data.
• Developing and running Solr queries to analyze repository records, metadata, indexing behavior, search results, and data-quality issues, and producing related reports.
• Comparing Digital Repository metadata with authoritative source systems, including Alma and ArchivesSpace, to identify discrepancies requiring correction.
• Evaluating and testing approved generative AI tools and agents for repository and discovery workflows, including prompt development, testing, output evaluation, and documentation.
• Reviewing OCR, captions, transcripts, audiovisual materials, and other digital content for quality, completeness, accessibility, and remediation opportunities.
• Testing approved methods to improve OCR, transcripts, metadata, and other machine-generated content, and conducting quality assurance after reprocessing or remediation.
• Conducting technical studies and supporting repository improvement, remediation, and migration projects with approved query, analysis, low-code/no-code, and AI tools.
• Researching relevant standards, tools, and approaches and documenting findings and develop recommendations.

Skills

Data analysis

Data quality

Metadata cleanup

Solr querying

Documentation

Communication

Public Trust clearance

Education

Bachelor's degree

Tools

XML

JSON

MODS

MARC-derived metadata

Alma

ArchivesSpace

Fedora

Solr

Blacklight

Job description

Computercraft provides a challenging role to support the National Library of Medicine (NLM) at NIH in Bethesda, Maryland. The Repository Services and Metadata Librarian will focus on technical information management, data analysis, quality control, and related tasks for the Digital Repository.

The role requires a Bachelor’s degree and two years’ experience with digital repositories and metadata, plus strong Solr querying and data-analysis skills.