RAG Pipeline Development

In this project, we're aiming to create an internal tool for companies to coagulate information and process the data they've curated. One task for this project is the establishment of simple RAG queries to enable fast access of the private company's database. In this project, students will be working with our team to help develop a RAG pipeline for acquiring information and summarizing data from the database. The primary goal for this project are as follows: Designing system architecture to detail the implementation of RAG Implementation of RAG towards secure database Development of key infrastructure for deploying and monitoring the application In this project, students will become familiar with working with generative AI for software products and then will help our company to continuously integrate RAG into our overall software product. Students will get the chance to work with a growing codebase and will have the chance to assist the team in building modern full stack applications. Most of the work revolves around development of server functions and as such, the students should ideally have prior experience with backend development.

REST API Development for Data Visualization and Feature Engineering

The main goal for the project is to develop a REST API that connects the main database of Puddl Software Ltd. to an external dashboard for data visualization and feature engineering. The API should be carefully built to ensure seamless integration and functionality with the external dashboard. This will involve several different steps for the students, including: - Understanding the main database structure and data flow within Puddl Software Ltd. - Developing the REST API endpoints for data retrieval and manipulation. - Creating documentation for the developed API endpoints. - Testing the API functionality and ensuring it meets the requirements for data visualization and feature engineering.

Data Engineering Pipeline Project

The main goal for the project is to create a data engineering pipeline for parsing data from the main application into the ML models of Puddl Software Ltd. This will involve the following steps for the student: - Understanding the data obtained from the primary app - Building a part of the data engineering pipeline to connect the dataset to the ML pipeline - Assisting in connecting the data to the ML models

Competitor Behavior Analysis Web Application

The main goal for the project is to have students work on a full-stack web application designed specifically for competitor behavior analysis. The students will need to help build a series of private features onto the Express, React, and Node.js application. This will involve working with the Puddl Software Ltd. team to understand the requirements and then building and presenting the finalized features.

Custom Data Pipeline and Anomaly Detection Project

The main goal for the project is to design a custom data pipeline using Python and custom backend REST APIs with Express, and then implement custom ML algorithms for anomaly detection. The project will involve researching data pipelines, designing and implementing them, and finally developing and integrating custom ML algorithms for anomaly detection.

Backend CRUD Application Development

The main goal for the project is to build a backend CRUD application for keeping track of internal private competitor data. This will involve developing a series of REST APIs for management of special internal databases using Node.js, React, and Express. The student will assist in the development of these APIs.

Data Visualization Dashboard for Competitor Analysis

The project's goal is to set up a data visualization dashboard with Python and SQL for competitor analysis data. We have already built a competitive landscape for our company and have knowledge of our competitors but now we want to build some visualizations and do some analysis of them using data visualization. We need a pipeline that will be updated as our database updates. If time permits, we'll also work on deploying created scripts onto our servers and setting up some update notifications for the team to continuously get notified of when the pipelines and a log report of the run. The scope of this project only involves building a key set of pre-defined visualizations and a pipeline that takes the SQL data and then visualizes them in Python. This project will not include any competitor analysis or other related research.

Data Engineering for Business Ecosystem Analysis

The main objective of this project is to set-up a full-scale data pipeline that takes in consumed data from our businesses analytics dataset and then passes it forward into a set of specially designed features. In this task, the student will be helping our team in completion of this pipeline and the student will be specifically focused on a set of specific data engineering tasks. The finished product will be a design doc detailing all the inner workings of the pipeline, completed GitHub tickets, and a repo containing all the work done during this project.