The project aims to enhance the data pipeline for a new AI tool being developed by Atlantis AI. The primary goal is to gather and process data from various online sources to optimize it for Retrieval Augmented Generation (RAG), a cutting-edge AI technology.

- Seeking a highly-motivated student intern to assist with the data pipeline of a new AI tool

- Job responsibilities will include gathering data from online sources, processing the data to optimize for Retrieval Augmented Generation (RAG), and implementing a demo of the data in use

- Additional responsibilities may include building a maintainable pipeline to update the sourced data

- Skills required include Python, data analysis, software development, interest in AI, exposure to the latest technologies in AI including LLMs and RAG

- An opportunity to learn about the AI tool development process and gain exposure to the latest technologies

• A demo application where a user can query a topic, and the system fetches data from the pipeline to generate a response using RAG.
• A brief presentation demonstrating the RAG tool in action, highlighting data retrieval and generation capabilities.
• A small list on the sources chosen, their relevance, and the data collection methodology.