University of North Carolina at Chapel Hill logo

University of North Carolina at Chapel Hill

AI/LLM Developer/Engineer

🇺🇸 Chapel Hill, NC

🕑 Temporary

💰 $26 - $34 per Hour

💻 Software Engineering

🗓️ July 28th, 2025

Langchain LLAMA Python

Edtech.com's Summary

The University of North Carolina at Chapel Hill is hiring an AI/LLM Developer/Engineer to join the Center for Virtual Care Value and Excellence (ViVE) AI research team. The role involves designing, fine-tuning, and evaluating large language models customized for healthcare applications, building intelligent LLM-based systems, developing scalable pipelines, and collaborating across disciplines to advance healthcare delivery through AI innovation.

Highlights
  • Design, fine-tune, and evaluate domain-specific large language models (LLMs) using transfer learning, LoRA, and RLHF.
  • Develop intelligent applications such as chatbots, virtual agents, clinical decision tools, and document analyzers using LangChain, LlamaIndex, or semantic search.
  • Build scalable LLM infrastructure for data ingestion, preprocessing, model serving on GPU/TPU, and continuous monitoring.
  • Integrate commercial and open-source LLMs (e.g., OpenAI GPT, Claude, Mistral, LLaMA) into digital health or enterprise systems via APIs or local deployment.
  • Apply advanced prompt engineering and chain-of-thought methods to enhance output accuracy, tone, and relevance.
  • Implement retrieval-augmented generation (RAG) architectures using vector databases like Pinecone, FAISS, or Weaviate.
  • Evaluate LLMs using automated and human-in-the-loop approaches focusing on accuracy, safety, hallucination, and user satisfaction.
  • Collaborate with data scientists, UX designers, domain experts, and MLOps to ensure effective and responsible AI deployment.
  • Monitor and optimize system performance metrics including latency, throughput, token usage, and cost-effectiveness.
  • Required qualifications include a Bachelor’s degree in Computer Science or related field with relevant experience, proficiency in Python and deep learning frameworks (PyTorch, TensorFlow, Hugging Face Transformers, LangChain), and familiarity with clinical healthcare data.
  • Preferred skills include distributed parallel training, multi-modal foundation models, hands-on LLM fine-tuning, prompt engineering, RAG experience, and cloud deployment of ML models.
  • Compensation ranges from $26.04 to $33.85 per hour for this full-time temporary position lasting up to 11 months.