Intern Placement QAA project Deployment Interface for a Geotechnical LLM ER

Deployment Interface for a Geotechnical Large Language Model

We are seeking a capable placement student to deliver the deployment component of a QAA-funded project developing a discipline-aware AI tool for engineering education. The role supports the pre-deployment phase of a collaboration between the Universities of Cardiff, Manchester, Surrey, and Glasgow, wrapping a fine-tuned language model in a secure, student-facing interface hosted on Cardiff ARCCA infrastructure ahead of autumn 2026 classroom rollout. 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:

Interface Development (55%)

• Build a browser-based interface that wraps the fine-tuned model endpoint, with session handling, query UI, and response presentation
• Integrate authentication compatible with Cardiff institutional identity where feasible
• Containerise the interface for deployment on Cardiff ARCCA infrastructure
• Expose basic usage telemetry to support evaluation during the controlled pilot

Testing and Handover (30%)

• Produce controlled-pilot test cases and user-acceptance checks prior to classroom rollout
• Support bug-fix cycles during the Phase 3 pilot

Documentation and Reporting (15%)

• Contribute to project interim outputs, progress reports, and dissemination materials

Required Skills and Attributes

• Background in computer science, software engineering, or a closely related discipline
• Confident in at least one modern web framework such as React, Vue, or Svelte
• Familiarity with Docker and REST API integration

Desirable Experience

• Experience implementing authentication via OAuth, OIDC, or SAML
• Exposure to large language model APIs or model-serving infrastructure
• Prior experience deploying to institutional HPC or cloud environments

Support and Development

The successful candidate will work under direct supervision of Dr Evan Ricketts, with technical liaison to Cardiff ARCCA. This position represents an excellent opportunity for computer science students to gain hands-on experience building a production-grade interface to a research language model that will be deployed across four UK universities; a strong portfolio piece and a direct contribution to a published research output. 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.