EBSCO Information Services (EIS) provides a complete and optimized research solution comprised of e-journals, e-books, and research databases - all combined with the most powerful discovery service to support the information needs and maximize the research experience of our end-users. Headquartered in Ipswich, MA, EIS employs more than 2,700 people worldwide, most now working hybrid or remotely. We are the leader in our field due to our cutting-edge technology, forward-thinking philosophy, and outstanding team. EIS is a company that will motivate you, inspire you, and allow you to grow. Our mission is to transform lives by providing relevant and reliable information when, where, and how people need it. We are looking for bright and creative individuals whose unique differences will allow us to achieve this inclusive mission around the world.

At the intersection of product management, data engineering, and customer-based interface design, sits the knowledge engineering team. The knowledge engineering team operates in a multi-faceted role. They perform complex data analysis to prioritize the greatest opportunities to improve knowledge representation of controlled vocabularies, knowledge extraction from full text, and bibliographic data. This team, siting within search, helps develop data pipelines that bring a multitude of data sets into the EBSCO knowledge graph, and they help define new data elements to help in the users’ search for scholarly content. Members of the team own the end-to-end development of knowledge graph features for EBSCO search, query expansion, disambiguation, and visual search within the EBSCO product lines.

Growing the Knowledge Graph requires the development of knowledge models describing how entities relate to one another for topical and bibliographic search and discovery. We use machine learning, linked data, and semantic techniques to create the graph as well as deduplication, entity extraction, matching of subjects and entities from our millions of full text records. In addition, we also use graph-ML techniques like shortest path, random walk, betweenness centrality, and Louvain modularity to gain insight from the knowledge graph for use in search aids on product.

As a Knowledge Engineer on the Knowledge Graph team, which consists of architects, knowledge engineers, taxonomists, and UX designers. You will contribute to the knowledge organization of EBSCO’s metadata assets, primarily multilingual controlled vocabularies, knowledge extraction, and bibliographic metadata, by modeling metadata schema, analyze graph structures and content, develop new semantic representations, and work with providers and consumers of data to guide the development and usage of knowledge structures to improve entity accessibility and enable automated reasoning. You will use a variety of semantic modeling techniques, judging tradeoffs between formality and usability for the knowledge extracted from content. You will also be establishing ETL processing rules and data processing workflows, working with linked data, mining for data internally and externally, and collaborating with the Product Management, Search, and Architecture teams in order to improve the search and semantic enrichment of EBSCO products through graph technology and data visualization methods.

Required Qualifications:

Education : Master’s in Information Science, Computer Science or Computational Linguistics or related field. Research focus on: search engine optimization, information retrieval, social network or scholarly modeling, ontology, knowledge graph, semantics, taxonomies, or semantic extraction rom full text

• 3+ years’ experience and/or a masters’ degree in information science, Library Science, computer science (specifically metadata or a related field), computational linguistics, or a related degree.
• Has 2+ years’ experience using controlled vocabularies such as taxonomies, ontologies, or knowledge graphs within search architectures
• Has 2+ years’ experience using graph technology such as property graphs or triple stores
• Has 2+ years’ experience or certificate/training in using W3C standards related to linked and canonical data and ontologies, in particular JSON, XML, DITA, RDF, RDFS, OWL, and/or SKOS.
• Has 1+ years’ experience using metadata schemes such as SKOS, Schema.org, Dublin Core, and/or Friend Of A Friend
• Has 1+ years’ experience integrating linked data and ontology data sets such as ORCID, CrossRef, Ringold, WordNet, Getty, Dbpedia, Bioportal ontologies, or similar data sets. 
• Has proficiency in SQL and SPARQL
• Has proficiency in Python or Java and/or NLP tools on AWS such as Comprehend, Rekignition, Sagemaker, or related machine learning tools
• Ability and willingness to learn new technologies and tools.

Preferred Qualifications :

• Semantic Web Technologies
• Knowledge Discovery and Knowledge Mining
• Basic Natural Language Processing (NLP) skills
• AWS Environment
• Knowledge in data visualization tools/techniques
• Knowledge in bibliometrics, impact factors, and citation analysis
• Detail-oriented and an ability to problem-solve independently. 
• Strong reading and writing skills.
• Very strong social and communication skills – ability to present ideas clearly and with confidence. 
• Ability to work individually and with a team to meet deadlines. 
• Familiarity with multilingual terminologies, taxonomies, ontologies, or scholarly articles.
• Familiarity with scraping websites, using APIs, and/or Search Engine optimization (SEO)

COVID VACCINATION REQUIREMENT: As directed by Executive Order 14042: Ensuring Adequate COVID Safety Protocols for Federal Contractors, all current and newly-hired EIS employees in the United States are required to be fully vaccinated by January 18, 2022 or by their date of hire.
We are an equal opportunity employer and comply with all applicable federal, state, and local fair employment practices laws. We strictly prohibit and do not tolerate discrimination against employees, applicants, or any other covered persons because of race, color, sex, pregnancy status, age, national origin or ancestry, ethnicity, religion, creed, sexual orientation, gender identity, status as a veteran, and basis of disability or any other federal, state or local protected class. This policy applies to all terms and conditions of employment, including, but not limited to, hiring, training, promotion, discipline, compensation, benefits, and termination of employment. We comply with the Americans with Disabilities Act (ADA), as amended by the ADA Amendments Act, and all applicable state or local law.