We are excited to offer an internship position for an AI project focused on the development and implementation of a Large Language Model (LLM)-based chatbot. This project involves creating an on-premise hosted model with which users can interact via a frontend interface to ask questions about company-specific documents. The system supports document uploads and maintains a chat history for each user. More specifically, it is a Retrieval-Augmented Generation (RAG) system.

• Backend Development: Built in Python using LangChain and Llama3.1 as the model.

• Authentication: Managed through an OAuth proxy.

• Routing: Handled by Nginx.

• Frontend Development: Created using Svelte to provide the chat interface for users.

• Basic knowledge of Python

• Understanding of Large Language Models (LLMs)

• Familiarity with AI concepts, Retrieval-Augmented Generation (RAG)

• Proficiency with Git

• Knowledge of Svelte

• Proficiency in HTML and CSS

• Experience with Git

• Understanding of Nginx

• Experience with Keycloak, Docker, OKD (OpenShift Kubernetes Distribution)

• Proficiency in Shell scripting

• Knowledge of Ansible

• Familiarity with Git