I am a dedicated Computer Science Engineer currently advancing my expertise through a Master’s in Software Engineering at Carnegie Mellon University, with a special focus on Machine Learning, Cloud Computing, and Distributed Systems.
Reach out on: rithiks@andrew.cmu.edu for opportunities.
Master of Software Engineering - Scalable Systems, 2023
Carnegie Mellon University
B.Tech in Computer Science, 2021
Shri Govindram Seksaria Institute of Technology and Science
Diploma in French, 2018
Alliance Française de Bhopal
Secondary School, PCM - IP, 2016
Delhi Public School, Indore
Developed an API for combating the coronavirus pandemic that creates SQL queries and graphical representations from NLP queries on the COVID19 dataset. The API has an accuracy of 84% and generates a PDF explaining the safety precautions with the help of diagrams and graphs.
Developed a machine learning model to classify DDoS attacks and benign traffic and compared the results using different learning algorithms.
Developed member directory application on Android Studio using Java Programming Language and SQLite as a database. The app features are - User Profile, Notification, Search, Night Mode, and Information log to admin.
Developed a real time flight costs comparison website using selenium to scrape fare from different website.
Sales Analysis Website built during the agile training program offered by CIDI, SGSITS.
This is a demonstration of how can we store information using version control and relational database model system.
Virtual Trials with the help of Augmented Reality to try cloths virtually before purchasing.
Designed a website that displays the previous election results in the form of a geographical map with the election memorandum of parties, the top 10 trending news, and helps citizens learn about politics.
This study focuses on the rise of Distributed Denial of Service (DDoS) attacks, exacerbated by the increase in Internet of Things (IoT) devices. Such attacks, like those against Amazon Web Services, GitHub, and BBC, cause significant disruptions and financial losses. The research aims to detect and mitigate these attacks early by comparing various supervised learning algorithms on the CIC-IDS 2017 dataset, utilizing a feature set created through five statistical methods and the Smart Detection feature selection algorithm.