Digital Repository Metadata Librarian — AI QA & Data Quality

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

Benefits offered by this job

Health, dental, vision, disability and

Life insurance

401(k) with matching

Paid leave 128 hours/year

11 paid holidays

40-hour work week

Job summary

Computercraft Corporation is seeking a Repository Services and Metadata Librarian to support the National Library of Medicine (NLM) at the NIH in Bethesda, MD. This full-time, hybrid role requires three days on site each week, working to enhance the Digital Repository and ensure data quality across metadata and content.

The role involves analyzing metadata, building Solr queries, evaluating AI-assisted workflows, and coordinating with Alma/ArchivesSpace integrations.

Qualifications

• Bachelor's degree required.
• Two years 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 analyze search/index data.
• Working knowledge of structured metadata formats (XML, JSON, MODS, MARC-derived)
• Experience with spreadsheets, query tools, text-processing tools, or lightweight scripting; programming 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 issues.
• Developing and running Solr queries to analyze repository records and data-quality issues.
• Comparing metadata with Alma and ArchivesSpace to identify discrepancies.
• Evaluating generative AI tools for repository workflows, including prompt development and testing.
• Reviewing OCR, captions, transcripts, audiovisual materials for quality and accessibility.
• Testing methods to improve OCR, transcripts, metadata, and machine-generated content.
• Supporting repository improvement, remediation, and migration projects with query/low-code/AI tools.
• Researching standards, tools, and approaches and documenting findings.

Skills

Data analysis

Metadata cleanup

Solr queries

Communication

Documentation

Education

Bachelor's degree

Tools

Solr

Alma

ArchivesSpace

XML

JSON

MODS

Job description

Computercraft Corporation is seeking a Repository Services and Metadata Librarian to support the National Library of Medicine (NLM) at the NIH in Bethesda, MD. This full-time, hybrid role requires three days on site each week, working to enhance the Digital Repository and ensure data quality across metadata and content.

The role involves analyzing metadata, building Solr queries, evaluating AI-assisted workflows, and coordinating with Alma/ArchivesSpace integrations.