My Resume

AI Research Engineer Intern

June 2025 - Present

PONS, Newark, NJ

Conducting research on GAN-based medical image synthesis using SPADE normalization, deployed and trained on Google Cloud Platform (GCP). Focused on generating high-fidelity medical images to enhance diagnostic accuracy and support clinical decision-making.
Graduate Research Assistant

April 2025 - Present

Stevens Institute of Technology, Hoboken

Conducting research on the application of LLMs and autonomous agents in financial NLP, focusing on tasks like sentiment analysis, temporal event extraction, and knowledge retrieval. Exploring agent-based architectures integrated with RAG and tool-augmented reasoning for enhancing investment decision support and real-time market analysis.
M.S. Computer Science

2024 - Present

Stevens Institute of Technology

Course Content: Algorithms, System Programming, Machine Learning: Foundation & Application, Knowledge Discovery and Data Mining, Natural Language Processing, Deep Learning, Statistical Machine Learning, Generative AI.
B.E. Electronics And Communication

2019 - 2023

JSS Science and Technology University

Course Content: Data Structure and Algorithms, Computer Networks, Digital Signal Processing, CMOS VLSI, Low Power VLSI, MEMS, Cryptography, Automotive Cybersecurity, Sensors & Instrumentation.
Software Engineer Intern

Aug 2021 - May 2022

FutureWave, Mysuru

Led app development with collaborative coding, debugging, and feature integration, refining HTML, CSS and JS skills, achieving a 0.2 drop in app crashes and 0.15 higher user engagement. Contributed to cross-functional teams, enhancing code quality and shortening the development cycle by 25% through effective code reviews.

Languages

English

Kannada

Hindi

Technical Skills

Python

TensorFlow

PyTorch

NLP

Computer Vision

Deep Learning

Machine Learning

Data Preprocessing

Feature Engineering

SQL

AWS

GCP

Docker

Git

Data Visualization

Prompt Engineering

LLMs

RAG

Model Deployment

Flask

Scikit-learn

Statistics

Data Mining

My Projects

Cloud Mart: Multi-Cloud based E-commerce Platform

Designed a multi-cloud e-commerce platform using AWS EKS for containerized microservices, with CI/CD via GitHub, CodePipeline, and Terraform. Integrated OpenAI, serverless Lambda, DynamoDB, S3, and Google BigQuery for analytics, while utilizing Azure AI for enhanced customer insights.

Learn More

RAG Based Web Scrapper

Developed a RAG-based web scraper using LangChain, OpenAI, and FAISS for efficient document retrieval and response generation. The system utilizes FAISS for high-speed vector search and semantic similarity matching, all wrapped in an interactive Flask-based UI for seamless query processing and real-time data extraction.

Learn More

AI Powered Skill Gap Analyzer

This Flask-based application features three AI-powered tools: an AI Mentor providing personalized tech advice, a Course Recommender suggesting relevant courses, and a Skill Gap Analyzer that identifies knowledge gaps. Designed with a clean Bootstrap interface, it offers seamless guidance for users seeking career development.

Learn More

Community Risk Monitor

This is a real-time safety monitoring app powered by React, TypeScript and CrewAI. It features an AI assistant ("Hey Attila"), integrating Crime API, NewsAPI, Open Weather API, WeatherGov API, Google Maps, and Web Speech API for location-based alerts, fire tracking, crime stats, weather updates, and traffic insights.This project secured 2nd place in the Chubb Challenge at Quack Hacks Hackathon.

Learn More

Medical Knowledge Assistant using RAG

Developed a RAG-based medical knowledge assistant using a custom pipeline with FAISS for document retrieval and GPT-2 for response generation. Integrated PubMed API for real-time access to medical literature, improving query accuracy. Built an intuitive Streamlit frontend for seamless clinician interaction and efficient knowledge retrieval.

Learn More

My Certificates

Machine Learning

Machine Learning Specialization by DeepLearning.AI & Stanford

My Publications

Systematic Review on Frameworks for Intrusion Detection using Machine Learning and Deep Learning Algorithms

Abstract:These days, information technology-driven businesses and companies are primarily concerned with cybersecurity challenges and their increasing complexity. Computer systems are still quite susceptible to several kinds of assaults, even with the introduction of multiple intrusion detection systems to combat zero-day cybersecurity threats. This sophisticated cyberattack has led to severe revenue losses in previous years due to several system breakdowns and service disruptions and irreversible harm to one’s reputation. This research paper provides an extensive, methodical analysis of cyberattacks. In addition to making thorough comparisons between the papers published by reputable venues in this field from a variety of angles. To greatly increase business sustainability, private corporations, governments, and enterprises can greatly benefit from implementing the survey paper’s results and major conclusions in their local or worldwide operations. By conducting a literature review, providing preliminary details on the various intrusion detection algorithms, and evaluating their performance while considering various parameters, this study strives at investigating the machine learning and deep learning-based strategies for intrusion detection systems.

Cloud Based Online Bus Ticket System

Abstract:The current system for booking bus tickets is reliant on humans and can be cumbersome. This project aims to develop a web application that simplifies the ticket booking process, allowing students, employees, and anyone else to easily book bus tickets. Unlike existing applications that only provide information on travel destinations and fares, the application not only facilitates ticket booking but also stores the tickets in a secure cloud database. Users can purchase tickets using their smartphones or laptops through the web application, eliminating the need to carry physical railway tickets. The ticketing information is securely stored in the cloud database, and a ticket checker application is provided to authenticate user tickets. The ticket checker can search for a user’s ticket in the cloud database using the ticket number or relevant information for verification purposes. In case a user’s display is damaged or there are issues like battery failure preventing the display of the ticket, there was an alternative safeguard option. The ticket can be validated by searching the ticket database using the ticket number or other relevant user information.

Design of Energy Harvester using Piezoelectric Material

Abstract: This paper offers an extensive examination of energy harvesting approaches, with a special focus on the utilization of piezoelectric energy harvesting. This method capitalizes on the unique capability of specific materials to produce an electric field when subjected to mechanical forces, a phenomenon termed the direct piezoelectric effect. Piezoelectric transducers are available in various forms and materials, rendering them adaptable for a wide array of applications. In addition to this, the paper delves into the significance of modeling the behavior of piezoelectric materials in both the time and frequency domains to enhance their utility. Additionally, it investigates several circuit configurations designed to optimize the efficiency of energy harvesting from piezoelectric devices

Karoke Audio Exarction Using Matlab

Abstract: To isolate sound sources in an audio scene is called audio source separation. Singing voice extraction is one use for source separation. Using the 2D Fourier Transform (2DFT), we provide a unique method for music/voice separation in this study. Our method takes use of the way periodic patterns appear in the 2D Fourier Transform and is related to studies on biological auditory systems and picture processing. We discover that our technique is relatively easy to describe, put into practice, and is competitive with existing unsupervised source separation methods that make use of related presumptions. Keywords: Automatic karaoke, foreground/background separation, image processing, 2DFT, audio source separation, singing voice extraction.

Who am I ?

Graduate Student in the Department of Computer Science at Stevens Institute of Technology, Hoboken, NJ

Personal Info

My Expertise

AI/ML Researcher

Machine Learning Engineering

Data Science

My Resume

AI Research Engineer Intern

Graduate Research Assistant

M.S. Computer Science

B.E. Electronics And Communication

Software Engineer Intern

Languages

English

Kannada

Hindi

Technical Skills

Python

TensorFlow

PyTorch

NLP

Computer Vision

Deep Learning

Machine Learning

Data Preprocessing

Feature Engineering

SQL

AWS

GCP

Docker

Git

Data Visualization

Prompt Engineering

LLMs

RAG

Model Deployment

Flask

Scikit-learn

Statistics

Data Mining

My Projects

Cloud Mart: Multi-Cloud based E-commerce Platform

RAG Based Web Scrapper

AI Powered Skill Gap Analyzer

Community Risk Monitor

Medical Knowledge Assistant using RAG

My Certificates

Machine Learning

My Publications

Systematic Review on Frameworks for Intrusion Detection using Machine Learning and Deep Learning Algorithms

Cloud Based Online Bus Ticket System

Design of Energy Harvester using Piezoelectric Material

Karoke Audio Exarction Using Matlab

My Achievements

Graduate Peer Mentor

(2025-Present)

System Designer

(2021-2023)

Community Volunteer

(2019-2023)

IEEE SJCE - Student Volunteer

(2020 - 2021)

Volunteer - Project ReachOut

(2021 - 2022)

SBMDC Ambassador

(2021 - 2022)

SBMDC Vice-Chairperson

(2022 - 2023)

SAC Coordinator

(2022 -2023)

Public Relations - Sahas Adventure Club

(2021 - 2023)

Send a message

Get in touch

Phone : + (201) 705-6654

Address : Jersey City, NJ - 07306

Email : amruthakravishankar@outlook.com

Phone :
+ (201) 705-6654

Address :
Jersey City, NJ - 07306

Email :
amruthakravishankar@outlook.com