The 2025 EBSCO Semantic Enrichment internship is an opportunity for a college student that wants hands-on experience exploring search analytics, machine learning, and generative AI technology on world-class search platforms and large-scale content sets in a B2B organization that serves top academic institutions and libraries around the world.
This remote position is U.S.-based only (excluding U.S. territories), with required working hours 9am – 5pm EDT
As part of the EIS Summer Intern Program, interns receive a dedicated orientation program starting on June 2nd and participate in enrichment and training events with fellow interns across the company. To learn more about the EIS Summer Internship Program, please visit - https://www.ebsco.com/about/internship-opportunities
Partner with the Semantic Enrichment and Search teams to explore new techniques and applications of machine learning and generative AI technologies including Retrieval Augmented Generation (RAG), prompt engineering, function calling, and embeddings and vectorization
Develop strong requirements by investigating workflows, collaborating with stakeholders, and researching AI-based solutions
Collect and analyze large sets of data including search queries and events, metadata and full text data, providing reports and summarizing key findings to drive tangible business results
Your Team
You will be working at the intersection of the EBSCO Semantic Enrichment team and the EBSCO Search team. Semantic Enrichment is responsible for the maintenance of proprietary subject taxonomies, support for the EBSCO subject knowledge graph, the application of ML-based auto-classification of content for EIS proprietary databases, and the advancement of generative AI in the EBSCO content space. The Search team is responsible for continuously enhancing EBSCO’s already best-in-class search platforms through rigorous analysis of search relevance, relevancy tuning, and AI innovation.
Undergraduate or Graduate student graduating December 2025 or later, eligible to work in USA
Strong academic record
Enthusiastic interest in AI, machine learning, and/or search relevancy
Demonstrable proficiency in Python and large data sets
What sets you apart
Effective communication skills; concise, targeted, clear, and persuasive
Coursework focused on Computer Science, Information or Data Science, Library Science, Software Engineering, Artificial Intelligence, or Computational Linguistics
Familiarity with principles of taxonomies or ontologies, graph technology, content classification, or search analytics
Experience with AI or ML data platforms such as Microsoft Azure or Amazon Bedrock
Experience analyzing and manipulating unstructured and semi-structured data (PDF, XML, JSON)
What is our application process like?
Software Powered by iCIMS
www.icims.com