Senior knowledge graph & context engineer

Modelon AB; Lunds kommun; On-site; SEK 60,000 - 90,000; Full time

Job summary

Modelon AB in Lund is seeking a Senior Knowledge Graph & Context Engineer to design and build context layers that support AI-enabled workflows. The ideal candidate will have hands-on experience with knowledge graphs and strong software engineering skills to create production systems.

We're looking for someone who can turn structured and unstructured data into reusable context services, collaborating closely with product, data, and engineering teams to ensure performance and maintainability.

Qualifications

• Hands-on experience building knowledge graphs and context services.
• Strong software engineering skills for building production systems.
• Experience with various graph technologies and standards.

Responsibilities

• Design and build context layers for AI-enabled workflows.
• Model entities and relationships using semantic techniques.
• Work with teams to productionize graph and AI context services.

Skills

Knowledge graphs

Semantic modeling

AI decision support

Software engineering

Graph databases

Metadata enrichment

Entity resolution

Tools

Neo4j

AWS

SPARQL

Job description

Senior knowledge graph & context engineer

Lund

Product Development

Build the context layer behind AI-enabled workflows. We are looking for a hands‑on engineer with real experience in knowledge graphs, semantic modeling, retrieval, and grounding. You will turn fragmented knowledge, metadata, and documents into reusable, governed context services that support search, decision support, and next‑generation AI product capabilities.

Why this role matters

AI is only as good as the context it can trust. In products that support expert users and complex decisions, the challenge is not just calling an LLM. The challenge is representing knowledge, relationships, provenance, and constraints in a way that can be grounded, reused, and governed in real workflows.

What you will do

• Design and build the context layer that supports AI‑enabled workflows, semantic search, and decision‑support capabilities.
• Model entities, relationships, metadata, lineage, and domain concepts using knowledge graphs, taxonomies, ontologies, or equivalent semantic approaches.
• Turn structured and unstructured knowledge into reusable context services for AI use cases.
• Improve retrieval, grounding, metadata enrichment, chunking, ranking, and provenance patterns to increase relevance and trust.
• Work with product, backend, data, and domain teams to productionize graph, search, and AI context services with strong performance and maintainability.
• Embed governance, access rules, and quality controls into context pipelines and semantic services.

What we are looking for

We are looking for a strong engineer with hands‑on knowledge graph and context engineering experience, paired with the software engineering depth to turn those capabilities into production systems.

Required experience

• Hands‑on experience with knowledge graphs, semantic models, metadata models, ontologies, taxonomies, or graph‑based context platforms.
• Experience building retrieval, semantic search, grounding, RAG, or context orchestration pipelines for AI‑enabled systems.
• Strong software engineering skills and experience building production services, data pipelines, or APIs in Python, Java, TypeScript, Go, C#, or similar.
• Experience with graph databases, semantic technologies, search platforms, or related ecosystems in real projects.
• Solid understanding of metadata enrichment, provenance, and the trade‑offs between graph, search, vector, and relational approaches.
• Ability to work across structured and unstructured data and turn fragmented information into coherent, reusable context.
• Experience with Neo4j, Stardog, GraphDB, Amazon Neptune, or similar graph technologies.
• Experience with RDF, OWL, SKOS, SHACL, SPARQL, or equivalent semantic standards.
• Experience with vector search, hybrid retrieval, reranking, and relevance evaluation.
• Experience with entity resolution, controlled vocabularies, ontology‑driven integration, or knowledge governance.
• Familiarity with Azure, AWS, or GCP data and AI ecosystems.
• Familiarity with AI‑assisted development tools such as Cursor, OpenAI Codex, Claude Code, or similar.
• Knowledge engineering, ontology engineering, graph data platforms, or semantic search.
• Enterprise search, AI‑enabled information access, or context engineering for LLM applications.
• Technical product environments where context quality, provenance, and trust materially affect outcomes.
• Work on one of the most important problems in practical AI: making context reliable enough for real product workflows.
• Help shape the foundations for AI‑enabled search, decision support, and workflow capabilities.
• Solve hard engineering problems at the intersection of knowledge graphs, retrieval, semantics, and AI.