DESCRRIPTION
The Data Specialist at the UNC-Chapel Hill University Libraries will provide artificial intelligence (AI) and data support for a project funded by the Mellon Foundation called On the Books: AI-Assisted Archives. Previous phases of this project created textual datasets of Jim Crow-era session laws from North Carolina, South Carolina, and Virginia and used machine learning to identify likely Jim Crow laws. The next phase of the project will expand this work to include the state of Texas and will endeavor to identify both Jim Crow and Juan Crow laws. Additionally, the project will investigate broadly the potential use of various applications of artificial intelligence for archival research. Examples include creating text corpora from historical legal documents, generating descriptions of photograph collections, and performing handwritten-character recognition (HCR) on archival documents.
QUALIFICATIONS
Master’s or Bachelors and 0-2 years’ experience; or will accept a combination of related education and experience in substitution.
Experience using Python and/or R and relevant libraries for working with images, natural language processing, and working with application programming interfaces (APIs).
Knowledgeable about AI, including prompt engineering.
Experience using version control.
Experience developing technical documentation.
Experience working with data for projects in the social sciences and/or humanities.
Experience using AI tools for processing data.
Experience in building, training, evaluating, and tuning predictive models.