AI Triage Bot Enhancement for IT Ticket Classification

zofiQ, Inc is seeking to enhance its existing AI triage bot to improve the classification accuracy of IT tickets. The current system struggles with accurately categorizing company names, boards, ticket types, and subtypes, leading to inefficiencies in ticket resolution. The goal of this project is to refine the AI model to ensure precise classification, thereby streamlining the IT support process. Learners will apply their knowledge of machine learning and natural language processing to analyze the current system, identify areas for improvement, and implement solutions. The project will involve tasks such as data analysis, model training, and testing to achieve a more reliable classification system. By the end of the project, the team will have contributed to a more efficient IT support workflow at zofiQ, Inc.

AI Backend/Infrastructure Developer

The project involves developing a backend infrastructure to support the integration of a Large Language Model (LLM) proof of concept with a website frontend. The primary goal is to create a seamless AI data pipeline that facilitates the Retrieval-Augmented Generation (RAG) process within an LLM tool. This project will allow learners to apply their knowledge of Python programming, API development, and LLMs like GPT. The project will focus on designing a robust backend system that can efficiently handle data flow and support the deployment of LLMs. Learners will gain hands-on experience in integrating AI technologies with web applications, enhancing their understanding of AI infrastructure and deployment strategies. Requirements: - Proficient in Python - Knowledgeable about calling and developing APIs (Flask, Django, etc.) - Experienced using LLMs like GPT, Claude, Llama, and others Nice to have: - Experienced with LLM infrastructure like RAG and ReAct agents - Experienced with deploying LLM tools - Experienced with handling user authentication and web integration - Experienced with web-scraping using BeautifulSoup and/or Selenium