Shishir Kallapur

Shishir Kallapur

Northeastern University

👤 About Me

I am a graduate student at Northeastern University and have finished my Master’s in Artificial Intelligence with a specialization in Machine Learning. I am fascinated by the software and technology currently being developed to produce extraordinary results. I completed my Bachelor of Engineering in CS from NIE,Mysuru.

I’m passionate about innovation and love learning new things quickly. I believe in the power of technology to make a positive impact. I bring strong technical skills, adaptability, and a determined attitude to everything I do.

I believe that my technical skills, passion for innovation, and never willing to give up makes me a valuable asset to the team and I’m driven to use my skills to create meaningful change .I’m eager to explore opportunities where I can contribute and grow while making a difference.

Click here to view my CV.

💼 Experience

Amplifier Security — AI Product Intern
May 2024 - Aug 2024 (Summer)

  • Spearheaded a comprehensive benchmarking initiative for GPT models(GPT-3.5, GPT-4, GPT-4o) significantly enhancing Ampy’s response accuracy, speed, and overall performance.
  • Implemented guardrails and prompts that boosted topical relevance by 35%, reducing hallucinations.
  • Automated response evaluation with custom Python scripts, improving testing speed by 3x.
  • Implemented a Retrieval-Augmented Generation (RAG) system with LangChain using Pinecone as Vector DB, enabling contextual replies from proprietary unstructured data.

JPMorgan Chase & Co. — Software Engineer
Sept 2021 – Aug 2023

  • Overhauled ServiceNow Knowledge module, enhancing request resolution speed by 20%.
  • Integrated JIRA with ServiceNow to automate SDLC tracking and reporting, incorporating CI/CD automation best practices and reducing manual effort by 40%.
  • Delivered 5 reusable UI macros to streamline HR documentation workflows; improved HR team’s document update efficiency by 45%.
  • Introduced and deployed catalog automation features, reducing request handling time by 30%.

MiQ Digital — Software Developer Intern
Jan 2021 - Jul 2021

  • Implemented full-stack features using Spring Boot and AngularJS, enhancing platform performance and UX.
  • Integrated DSPs (Xandr, DV360) into internal tools, streamlining campaign activation and data processing.
  • Enabled DV360 as a viable DSP option, accelerating project timelines and increasing platform utility.

🚀 Projects

⚕️ CS6140: Relating Physical Activity to Problematic Internet Use in Youths

GitHub Repo
The project is based on a Kaggle Competition where the goal of this project is to develop a model capable of identifying the potential risk of problematic internet use among youths by utilizing relevant physical activity data and internet usage data.

⚕️ CS5180: Enhancing Bipedal Robot Locomotion Using Reinforcement Learning with Reference Signal Integration

GitHub Repo
This is our final project for CS5180 Spring 2024 under Professor Lawson L.S Wong. To add more details

⚕️ CS5010: Image Processor

GitHub Repo
This is our final project for CS5010 Fall 2023 under Professor Amit Shesh. The project is based on building an image processing application designed with MVC architecture.The application takes in an image and performs an operation on the input image to produce a desired outcome.

⚕️ CS5100: Adaptive Difficulty in Games: Leveraging Reinforcement Learning for Player-Driven Immersion

GitHub Repo
This is our final project for CS5100 Fall 2023 under Professor Rajagopal Venkatesaramani. The project utlizes Reinforcement Learning (RL) to create game levels that adapt to each player’s unique strengths, weaknesses, and preferences.The project also involved creating an Adversarial RL system to test both “Player” and “Environment” working together, where the player is trying to clear levels with ease whereas the “Environment” is continuously learning the “Player”s skills to make levels more difficult.

⚕️ CS6120: Comparative Analysis of nGPT, PEGASUS, and BART in Abstractive Text Summarization

GitHub Repo
This is our final project for CS6120 Fall 2024 under Professor Silvio Amir. This project aims to evaluate and compare the performance of nGPT (Nvidia’s model) against two state-of-the-art abstractive text summarization models: PEGASUS (Google) and BART (Facebook). The focus is on assessing nGPT’s claims of achieving 4-20x faster training times and improved stability for Large Language Models (LLMs) in the context of abstractive text summarization.

⚕️ CS5170: Emotion-Driven Audio-Visual Experience: Enhancing Human-Computer Interaction through Real-Time Multimodal Feedback

GitHub Repo
This is our final project for CS5170 Spring 2025 under Professor Stacey Marsella. This project explores an AI-driven system for generating immersive and personalized audio-visual experiences by detecting user emotions and intent in real time.

⚕️ Local Document-Powered RAG Chatbot

GitHub Repo
This project is a Streamlit application that enables users to upload PDF documents, process them for information retrieval, and interact with the content through a conversational interface powered by Large Language Models (LLMs) and RAG.

📖 Education

  • 2023.09 - 2025.05, Graduate, Northeastern University, US
  • 2017.09 - 2021.05, Undergraduate, The National Institute of Engineering, India

Last updated: Jul. 29, 2025