Knowledge Graph and AI Engineer

Kintec Global Recruitment; Manchester; On-site; GBP 65,000 - 90,000; Full time

Job summary

Kintec Global Recruitment is seeking a Knowledge Graph and AI Engineer in Manchester, UK, for building the knowledge graph and AI services behind a SaaS platform. The role supports extraction, entity resolution, and semantic search, with a focus on data provenance and evidence-backed matches.

You will implement RDF models, SHACL constraints, and Python-based services using FastAPI, ensuring data quality, privacy, and scalable processing.

Qualifications

• Experience building RDF knowledge graphs and ontologies in a production system.
• Proven ability to design classes, relationships and taxonomies for data-intensive domains.
• Strong Python development and API design with validation/testing.

Responsibilities

• Develop RDF models and ontology modules for candidate and vacancy data.
• Preserve source evidence and record changes within graphs.
• Write SPARQL queries and maintain taxonomy mappings with SHACL validation.
• Build Python services to map records into the graph and handle updates.

Skills

RDF Knowledge

Python

SPARQL

FastAPI

Graph Embeddings

Tools

SHACL

GraphDB/AWS Neptune

SQL

Job description

Knowledge Graph and AI Engineer

Location: Manchester, UK
Contract Type: Contract

About the Role

We are seeking an engineer to help build the knowledge graph and AI services behind a SaaS platform. You will be responsible for turning documents and records into structured information, connecting related data, and supporting search and matching with clear supporting evidence. This role is open to both senior and mid-level engineers with relevant practical experience.

Key Responsibilities

• Develop RDF models and ontology modules for candidate and vacancy data, including skills, qualifications, and employment history.
• Preserve source evidence, record changes, and represent conflicting information within the models.
• Write SPARQL queries, maintain taxonomy mappings, and use SHACL to validate graph data.
• Build Python services and repeatable processes to map structured records and extracted information into the graph, including incremental updates, duplicate handling, and pre-publication checks.
• Ensure corrections and approved deletions reach the graph and search indexes, respecting tenant boundaries and access permissions.
• Develop information extraction services for documents, messages, and transcripts using FastAPI and schema validation, ensuring source location and model version are retained.
• Contribute to entity resolution using identifiers and similarity methods, maintaining evidence behind matches.
• Support semantic and hybrid search using embeddings, metadata filters, and graph queries, evaluating results against representative examples with explanations grounded in source evidence.
• Write tests and maintain evaluation examples for built components, considering quality, latency, processing cost, and failure handling.
• Collaborate with colleagues on service integration, investigate issues, and document decisions for ongoing maintenance.

Requirements

• Professional software or data engineering experience, with a track record of delivering tested components within a team.
• Hands-on experience implementing an RDF knowledge graph and designing or extending an ontology in a working system, including SPARQL queries, defining classes and relationships, modelling taxonomies, and applying SHACL constraints.
• Ability to explain modelling choices and demonstrate handling of data quality or query problems.
• Practical experience with at least one RDF graph store (e.g., GraphDB, Stardog, Apache Jena, Amazon Neptune).
• Understanding of stable identifiers, named graphs, provenance, and relevant standards such as SKOS, PROV-O, and JSON-LD.
• Strong Python and SQL skills, experience building APIs with FastAPI or similar frameworks, and knowledge of schema validation and automated testing.
• Ability to integrate services with application data and handle errors, retries, and timeouts effectively.
• Practical experience in some of the following: information extraction, entity resolution, embeddings, semantic search, or retrieval evaluation.
• Clear communication of technical decisions and effective teamwork with other engineers.
• Understanding of data privacy, access controls, and the risks of sending sensitive information to model providers.
• Commitment to preserving uncertainty in AI outputs and following agreed human review controls.

Useful Additional Experience

• Experience with Azure, model evaluation tools (e.g., MLflow), or search platforms (e.g., Azure AI Search, OpenSearch).
• Experience in document processing, ontology versioning, graph query optimisation, event-driven processing, or deploying AI services.

Application Guidance

Please describe a knowledge graph or ontology you have worked on, your personal contribution, and the tools you used. We are interested in a modelling or implementation problem you encountered, your approach, and what you learned from the result.