Intern Placement QAA project Knowledge Graph Development for a Geotechnical LLM ER

Knowledge Graph Development for a Geotechnical Large Language Model

We are seeking a diligent placement student to support the knowledge-graph component of a QAA-funded project developing a discipline-aware AI tool for engineering education. The role supports a collaboration between the Universities of Cardiff, Manchester, Surrey, and Glasgow building an authoritative, structured grounding layer for a fine-tuned geotechnical language model intended for use in undergraduate teaching. In practical terms, the finished tool will be a specialist AI assistant for geotechnical engineering, used by undergraduate students across the four partner universities as a reliable, source-grounded alternative to general-purpose chatbots such as ChatGPT.

Key Responsibilities:

Source Curation and Ingestion (45%)

• Curate authoritative geotechnical source material and extending to partner-contributed content
• Apply the project's knowledge graph schema to the structured ingestion of curated material
• Maintain clear provenance and licensing records for all source material
• Document gaps in available source coverage to support targeted future acquisition

Graph Construction and Grounding (40%)

• Implement the ingestion pipeline, including LLM-assisted curation of source material where appropriate
• Assess grounding quality on the three known weak areas of the base model: procedural judgement, interpretative judgement, and negative testing
• Iterate the graph structure based on grounded-generation evaluation results from the benchmark intern

Documentation and Reporting (15%)

• Deliver a reusable knowledge graph release with ingestion scripts and schema documentation
• Contribute to project interim outputs, progress reports, and dissemination materials

Required Skills and Attributes

• Background in civil, geotechnical, or a closely related engineering discipline
• Strong grounding in geotechnical fundamentals, including classification, testing, and constitutive behaviour
• Methodical approach to structured data curation with clear, careful technical writing
• Familiarity with Python for data handling

Desirable Experience

• Exposure to knowledge graphs, ontologies, or semantic web concepts
• Prior use of generative AI or large language model tools

Support and Development

The successful candidate will work under direct supervision of Dr Evan Ricketts and Dr Fei Jin, with access to the wider project team and industry partners. This position represents an excellent opportunity for students interested in applied AI within civil engineering to gain hands-on research experience, contribute to a published domain knowledge graph, and build a portfolio in an emerging discipline-specific AI area. Interns will be named in project outputs and acknowledged in any research publications arising from their contributions, with the opportunity for co-authorship on strong individual contributions.