Student Assistant Technical Specialist for LLM Digital Twin RAG Pipeline

Classification Title:

Student Assistant Technical Specialist for LLM Digital Twin RAG Pipeline

Classification Minimum Requirements:

• Currently enrolled in a graduate or undergraduate program in Computer Science, Data Science, Biomedical Engineering, or a related field.
• Proficiency in Python and experience with machine learning libraries such as PyTorch.
• Strong understanding of NLP and transformer-based language models (e.g., BERT, GPT, LLaMA).
• Familiarity with basic concepts in information retrieval and vector search (e.g., FAISS, Elasticsearch).
• Ability to work independently and collaboratively in a fast-paced, research-driven environment.

Job Description:

The Intelligent Critical Care Center (IC3) is a multi-disciplinary center focused on developing and providing sustainable support and leadership for transformative medical AI research, education, and clinical applications to advance patients' health in critical and acute care medicine. The Center addresses an unprecedented opportunity for world-leading ambient, immersive, and artificial intelligence (AI2) research and innovation to transform the diagnosis, monitoring, and treatment for critically and acutely ill patients using the multimodal clinical and research data and resources from UF Health (UFH), one of Florida’s largest health care systems. 

With a growing team of 37 faculty, scientists, researchers, and students, IC3 aims to revolutionize critical and acute care medicine. We are idealists, problem solvers, and explorers of digital health and AI. We’re looking for team members who are driven and enthusiastic to be a part of our mission to use AI and digital technologies to advance health care so that critically and acutely ill patients can receive the best possible treatment when they need it the most. 

We are looking for motivated and qualified students to join our team and contribute to developing an LLM-driven chat bot aimed at enhancing patient care through advanced machine learning and natural language processing capabilities. This project involves creating a comprehensive AI system, including data curation, LLM fine-tuning, RAG pipeline, guardrails, and real-time interaction through text or voice chat.

Responsibilities: 

• Develop and deploy a Retrieval-Augmented Generation (RAG) pipeline, integrating structured and unstructured external knowledge sources to support accurate and context-aware chatbot responses.
• Fine-tune large language models (LLMs) using curated datasets relevant to patient care, optimizing performance for clinical dialogue and question-answering tasks.
• Implement and monitor safety guardrails, ensuring the AI companion adheres to ethical, privacy, and reliability standards in both text and voice-based interactions.
• Collaborate on data curation and preprocessing, including extracting, cleaning, and annotating healthcare-relevant data for training and inference stages.
• Support real-time deployment and testing of the chatbot interface, contributing to backend integration, user experience evaluation, and iterative model improvements.

Expected Salary:

$20/hr

Required Qualifications:

• Currently enrolled in a graduate or undergraduate program in Computer Science, Data Science, Biomedical Engineering, or a related field.
• Proficiency in Python and experience with machine learning libraries such as PyTorch.
• Strong understanding of NLP and transformer-based language models (e.g., BERT, GPT, LLaMA).
• Familiarity with basic concepts in information retrieval and vector search (e.g., FAISS, Elasticsearch).
• Ability to work independently and collaboratively in a fast-paced, research-driven environment.

Preferred:

• Hands-on experience with RAG architectures and LLM fine-tuning.
• Prior work involving LangChain, LlamaIndex, or similar LLM orchestration frameworks.
• Experience developing safety guardrails or prompt engineering strategies for LLM-based applications.
• Background in healthcare, clinical informatics, or biomedical data applications.
• Familiarity with Docker, APIs, and deploying ML pipelines in production or research environments.
• Ability to plan, organize, and coordinate work assignments. 
• Ability to communicate effectively, both verbally and in writing. 

Special Instructions to Applicants:

Application must be submitted by 11:55 p.m. (ET) of the posting end date.

Health Assessment Required: No