LMS Research Internship: Developing the Foundations of an AI-Assisted Research Assistant
Closing Date: 08/09/2026

Title: LMS Research Internship: Developing the Foundations of an AI-Assisted Research Assistant for Biomedical Raman Spectroscopy

Please note: this internship is only available to current undergraduate students in Lancaster University Medical School.

This internship is offered as part of an exciting pilot of research opportunities for Medical School undergraduate students (MBChB and SaES). Each internship will be supervised by an academic member of staff. These opportunities are designed to give students experience of contributing to university research. These internships would be ideal for students considering postgraduate study, intercalated degrees or specialised foundation programmes.

Biomedical Raman spectroscopy is an emerging analytical technique that provides detailed molecular information from biological tissues and has important applications in musculoskeletal research, cancer diagnostics, tissue engineering, and regenerative medicine. Despite its growing use in biomedical research, interpreting Raman spectra and identifying relevant scientific evidence remains challenging because it requires expertise across spectroscopy, biomedical science, data analysis, and scientific literature.

Recent advances in Artificial Intelligence (AI), particularly Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), offer new opportunities to support researchers by retrieving, organising, and summarising scientific evidence. Rather than replacing researchers, these technologies can improve literature discovery, support evidence-based interpretation, and accelerate research workflows.

This internship represents the first stage of a broader research programme to develop an AI-assisted research assistant for biomedical Raman spectroscopy. Working closely with the supervisors, the student will gain hands-on experience in biomedical research while learning the fundamentals of Raman spectroscopy, AI, scientific programming, and research data management. The student will help develop an initial proof-of-concept literature retrieval system using a curated collection of biomedical Raman spectroscopy publications.

The project has been specifically designed for undergraduate students with limited or no previous research experience. A structured programme of weekly supervision, practical workshops, and guided independent learning will provide training in scientific literature searching, critical appraisal, Python programming, AI concepts, and responsible use of emerging technologies in biomedical research.

By combining biomedical science with modern AI methods, this project will provide valuable interdisciplinary research experience while developing transferable skills in scientific communication, data organisation, programming, critical thinking, and collaborative research. These skills are increasingly sought in academic research, healthcare, biotechnology, and medical technology industries, providing an excellent foundation for students considering future research careers or postgraduate study.

Major duties:

Throughout the internship, the student will

• organise scientific publications into a structured knowledge base
• explore how Retrieval-Augmented Generation retrieves relevant evidence from published literature
• build and evaluate a simple prototype literature retrieval workflow
• critically assess AI-generated responses against published scientific evidence
• The internship will conclude with a written report and oral presentation of the student’s work.

Please apply through ERS with:

1. A CV including your education history and any work experience (maximum of two full pages) and,
2. A cover letter that explains your interest in research, why you would like to be involved in this particular research internship, and how you meet the criteria outlined in the person specification.

• Creativity
• Curiosity
• Decisiveness
• Collaboration
• Planning and organising
• Problem solving
• Self-motivation
• Teamwork
• Time Management
• Verbal communication
• Written communication