Senior Data Scientist

Semantic AI & Knowledge Graphs

About Depixen

Depixen is a London-based technology company building the digital decision infrastructure of the construction industry.

As a corporate member of the World Wide Web Consortium — W3C, Depixen develops Linked Data architectures, domain-specific taxonomies, ontologies, RDF-based data structures, and knowledge graph infrastructures for construction, architecture, and building products.

We work with fragmented and highly contextual industry data: product catalogues, technical documents, standards, materials, suppliers, projects, events, images, and user interactions.

About the Role

We are looking for a Senior Data Scientist to help build intelligent data systems for classification, enrichment, entity resolution, semantic search, recommendation, and knowledge graph-connected AI applications.

This is not a conventional data science role. You will work at the intersection of machine learning, semantic data modelling, information retrieval, knowledge graphs, and real-world construction product data.

Your work will help turn fragmented industry data into reliable, contextual, and explainable decision intelligence.

Responsibilities

• Develop machine learning and data science systems for classification, extraction, enrichment, matching, recommendation, and semantic search.
• Work with structured, semi-structured, unstructured, and graph-connected data.
• Build entity extraction, entity resolution, deduplication, and similarity-matching workflows.
• Connect AI outputs with taxonomy, ontology, RDF, and knowledge graph layers.
• Design evaluation, benchmarking, validation, and error-analysis processes.
• Improve data quality, consistency, explainability, provenance, and semantic alignment.
• Collaborate with engineering, product, and domain teams to turn business requirements into scalable technical systems.
• Support the development of production-grade semantic AI and decision-support systems.

Required Qualifications

• Bachelor’s degree in Computer Science, Data Science, AI, Software Engineering, Mathematics, Statistics, or a related field.
• 4+ years of hands-on experience in data science, machine learning, information retrieval, NLP, knowledge graphs, or related AI/data fields.
• Strong Python skills.
• Experience developing, testing, deploying, and monitoring data science or machine learning models.
• Experience with structured, semi-structured, and unstructured data.
• Practical experience in several of the following areas:
• classification
• entity extraction
• entity resolution
• semantic enrichment
• recommendation systems
• semantic search
• information retrieval
• NLP
• data quality automation
• Strong understanding of data modelling, metadata, data quality, model evaluation, benchmarking, and error analysis.
• Ability to document technical work clearly and communicate across technical and non-technical teams.
• Interest in semantic web technologies, knowledge graphs, ontologies, taxonomies, or linked data.

Preferred Qualifications

• Master’s or PhD in Computer Science, AI, Data Science, Machine Learning, NLP, Semantic Web, Knowledge Graphs, or a related field.
• Experience with RDF, OWL, SPARQL, SHACL, SKOS, JSON-LD, schema.org, ontologies, taxonomies, or Linked Data.
• Experience with graph databases or triple stores such as GraphDB, Stardog, Neo4j, Amazon Neptune, or Blazegraph.
• Experience with embeddings, vector databases, RAG, LLM-based enrichment, or knowledge graph completion.
• Experience with MLOps tools such as Docker, Kubernetes, MLflow, Weights & Biases, Airflow, or similar.
• Experience with AWS, GCP, or Azure.
• Experience in construction, architecture, BIM, building materials, technical product data, catalogues, standards, or compliance-heavy data systems.
• Contributions to open-source projects, academic publications, or applied research are a plus.

Problem Areas

You may work on:

• construction product classification and enrichment;
• entity resolution for products, suppliers, events, venues, organizations, and technical concepts;
• semantic search and recommendation systems;
• extraction of structured data from catalogues, PDFs, websites, and technical documents;
• knowledge graph-connected AI workflows;
• data quality, explainability, provenance, and validation systems.

Why This Role Is Different

Construction data cannot be understood through statistical patterns alone. The meaning of a product, material, document, technical value, supplier, or project depends on its relationship to standards, classifications, specifications, and domain knowledge.

At Depixen, data science outputs are not isolated predictions. They are connected to verified data, semantic classification, ontology, RDF, and knowledge graph layers.

This role is about building reliable, contextual, explainable, and machine-interpretable AI systems for one of the world’s most complex industries.