The Job

Master Thesis: Open Knowledge Format

Teknik, data och digitalt · Mjukvaru- och webbutveckling · Mjukvaruutveckling · Artificiell intelligens · Data engineering

Gå med för uppdateringar

I korthet

This Master's thesis at Ericsson in Stockholm focuses on improving Customer Product Information (CPI) generation using AI. The project involves designing and implementing a prototype that utilizes metadata annotations, ontologies, and document templates with Open Knowledge Format and GraphRAG to dynamically assemble content and trace its sources.

Ansvarsområden

  • Review relevant literature and current approaches for documentation generation, knowledge representation, and graph-based RAG (GraphRAG).
  • Study CPI template requirements and define annotations and an ontology linking design concepts, topics, releases, and configurations.
  • Design and implement a FastAPI prototype that uses Apache Ossie to ingest design proposals, interface specifications, and schemas into validated OKF concept bundles, organised in a knowledge base and linked through an ontology-based knowledge graph.
  • Implement GraphRAG, combining vector search with graph traversal, so that LLMs assemble applicable topics with traceable references and flag missing evidence.
  • Identify the CPI topics affected when designs or template requirements change, regenerate them, and check that unaffected topics remain correct.
  • Create an appropriately protected dataset, including controlled changes to designs and template requirements, and establish reference topics reviewed by experienced CPI authors.
  • Compare results with the RAG baseline using measures such as claim accuracy, content coverage, citation validity, affected-topic precision and recall, correctness of regenerated topics, and authoring and review time.
  • Analyse limitations, data-quality dependencies, and suitable human oversight for CPI authoring.

Krav

  • Master’s-level studies in computer science, software engineering, or a related field.
  • Proficiency in Python, including asynchronous programming, and experience with LLM APIs, prompt engineering, and RAG.
  • Familiarity with FastAPI or a similar web framework, PostgreSQL or vector databases, and Docker.
  • Ability to work with structured and unstructured technical documentation.
  • Interest in empirical evaluation, technical documentation, and responsible AI.
  • Strong analytical, problem-solving, and communication skills.

Önskade kvalifikationer

  • Experience with knowledge graphs, RDF/OWL ontologies, OKF, data pipelines, frontend tooling, or open-source practices is an advantage.

Förmåner

  • Outstanding opportunity to use your skills and imagination to push the boundaries of what’s possible.
  • Be challenged, but not alone; join a team of diverse innovators.
  • Opportunity to craft what comes next.
  • Work in a diverse and inclusive organization that champions diversity.
#AI#Knowledge Graph#Ontology#RAG#LLM#Documentation#Master Thesis#Internship#Python#FastAPI#Docker#Apache Ossie
Ericsson Logo

Företag

Ericsson

Publicerade jobb

för 1 dag sedan

Anställningstyp

Praktik

Arbetsform

På plats

Erfarenhetsnivå

Student

Platser

Stockholm, Sweden

Kvalifikation

Masterexamen

Sökande

Ansök tidigt