AutoEdge AI empowers OEMs to seamlessly transform vehicle manuals and diagnostic data into deployable, vehicle-specific AI assistants.
Leveraging a hybrid architecture - a base automotive Small Language Model (SLM) combined with LoRA adapters and on-device Retrieval-Augmented Generation (RAG) - our platform enables OEMs to 'walk away' with a personalized and optimized AI solution that runs on edge.
Python
PEFT
QLoRA
RAG
Small Language Models
Vector DB
Chroma
PyTorch
Edge AI
Document Parsing
Embedding Models
Python
PEFT
QLoRA
RAG
Small Language Models
Vector DB
Chroma
PyTorch
Edge AI
Document Parsing
Embedding Models
—
Quad-AI Voice Assistant System
A real-time voice-based conversational AI orchestrator for Denso's Quad (formerly Parker) Vehicle System, that runs on Raspberry Pi.
Supports wake word detection, VAD, STT (AWS Transcribe, Faster-Whisper), TTS (AWS Polly), LLM integration via AWS Bedrock, AEC, and MCP tools for synchronous/asynchronous execution with progress polling.
Python
Rust
LLM
AWS Bedrock
STT
Faster Whisper
AWS Transcribe
TTS
AWS Polly
Wakeword Detection
PV-Porcupine
AEC
VAD
MCP
Docker
Raspberry Pi
OpenAI API
Python
Rust
LLM
AWS Bedrock
STT
Faster Whisper
AWS Transcribe
TTS
AWS Polly
Wakeword Detection
PV-Porcupine
AEC
VAD
MCP
Docker
Raspberry Pi
OpenAI API
—
Quad-Terminal
A web-based terminal for Denso's Quad (formerly Parker) Vehicle System, that runs on edge devices (Raspberry Pi, QualComm, Nvidia Jetson).
It enables interaction with Dockerized microservices via WebSockets and remote cloud access through port forwarding for debugging and testing purposes.
React
TypeScript
NodeJS
Docker
AWS ECS
AWS ECR
WebSockets
gRPC
AWS CDK
REST APIs
NGINX
Jest
React
TypeScript
NodeJS
Docker
AWS ECS
AWS ECR
WebSockets
gRPC
AWS CDK
REST APIs
NGINX
Jest
—
Quad-Installer
An NPM-based CLI tool for Denso's Quad (formerly Parker) Vehicle System, that handles lifecycle management of Dockerized microservices on edge devices.
Enables remote monitoring, automated deployment, and self-updating edge infrastructure via seamless cloud integration - managing Docker containers and systemd services with built-in job scheduling, prioritization, and continuous optimization.
TypeScript
NodeJS
Docker
SystemCTL
AWS S3
AWS Cognito
AWS CDK
gRPC
Jest
TypeScript
NodeJS
Docker
SystemCTL
AWS S3
AWS Cognito
AWS CDK
gRPC
Jest
—
District Development Model for India
Used Mass Media and Census data to develop a method for identifying relevant news articles that explain and analyze growth in Indian districts across Agriculture, Development, Lifestyle, Environment, and Industrialization.
Published in DSSG-21, KDD 2021. Provided actionable insights for district-level development analysis.
Doc2Vec
DocTag2Vec
TF-IDF
Hierarchical Clustering
K-Means Clustering
Glove-Embeddings
Doc2Vec
DocTag2Vec
TF-IDF
Hierarchical Clustering
K-Means Clustering
Glove-Embeddings
Similar Companies Recommendation System
Enabled automated discovery of similar companies for business intelligence and market research.
NLP-based system that recommends similar companies using Glove Embeddings, TF-IDF, Hierarchical Clustering, K-Means Clustering, and Cosine similarity.
Includes a Django web app deployed with Docker, AWS ECR, and AWS ECS.
Python
NLP
Glove Embeddings
TF-IDF
Hierarchical Clustering
K-Means Clustering
Cosine Similarity
Django
Docker
AWS
Python
NLP
Glove Embeddings
TF-IDF
Hierarchical Clustering
K-Means Clustering
Cosine Similarity
Django
Docker
AWS
—
Latex to HTML Compiler/Converter
Compiler to convert Latex code to HTML code.
Implements Abstract Syntax Tree along with the grammar.
Uses Flex and Bison as Lexical and Syntax Analyzer.
C
Flex
Bison
Compiler Design
Abstract Syntax Tree
C
Flex
Bison
Compiler Design
Abstract Syntax Tree
kon172verma.com Portfolio Website
Personal portfolio and interactive resume site built with Next.js, React, and TypeScript.
Features a chat assistant that uses RAG and OpenAI_API, and has dynamic project/experience sections, and a modern, responsive UI.
Website Design inspired by Brittany Chiang: www.brittanychiang.com
Next.js
React
TypeScript
Tailwind CSS
Vercel
OpenAI API
Next.js
React
TypeScript
Tailwind CSS
Vercel
OpenAI API
Autonomous Driving Vehicle
Designed an end-to-end self-driving car steering control system using Conv2D, Conv3D, and R-CNNs (Conv-LSTM) from live video feed, achieving 98% accuracy.
Demonstrated robust autonomous driving capabilities using deep learning architectures.
Python
Conv2D
Conv3D
R-CNN
Conv-LSTM
Deep Learning
Computer Vision
Python
Conv2D
Conv3D
R-CNN
Conv-LSTM
Deep Learning
Computer Vision
Malware Classification System
Used classical machine learning techniques such as Logistic Regression, KNN, Random Forests and XGBoost to classify malware into 10 classes with over 99.7% accuracy.
Python
Logistic Regression
KNN
Random Forests
Machine Learning
Python
Logistic Regression
KNN
Random Forests
Machine Learning
Paratroopers 3D Game
A 3D recreation of the classic 1980s Paratroopers game built using the Unity framework, featuring a turret-based defense gameplay system.
Designed core gameplay mechanics such as shooting physics, enemy AI behaviors, scoring system, and danger-level based game termination logic.
Unity3D
C#
Game Development
3D Graphics
Physics Simulation
Object-Oriented Programming
Unity3D
C#
Game Development
3D Graphics
Physics Simulation
Object-Oriented Programming
Parser Logical Form Generator
Developed a Prolog-based parser to convert structured English sentences into formal logical representations using predicate logic.
Implements rule-based parsing to generate quantified expressions, predicates, and relationships for natural language understanding tasks.
Prolog
Natural Language Processing
Predicate Logic
Parsing
Logic Programming
Prolog
Natural Language Processing
Predicate Logic
Parsing
Logic Programming
DCG Handler
Built a Prolog-based system to explicitly convert Definite Clause Grammar (DCG) rules into equivalent standard Prolog clauses.
Prolog
Definite Clause Grammar (DCG)
Logic Programming
Parsing
Compiler Design
Prolog
Definite Clause Grammar (DCG)
Logic Programming
Parsing
Compiler Design
NLP using Deep Learning
Implemented multiple NLP applications using deep learning, including text generation, sentiment analysis, sarcasm detection, and news classification.
Built and trained RNN and Bidirectional LSTM models on diverse datasets to perform sequence modeling and language understanding tasks.
Python
Deep Learning
NLP
RNN
LSTM
TensorFlow
Keras
Python
Deep Learning
NLP
RNN
LSTM
TensorFlow
Keras
Cryptocurrency Concoin Blockchain
Developed a basic blockchain system and extended it to build a functional cryptocurrency supporting mining, transaction handling, and chain validation.
Implemented a Flask-based interface and APIs to interact with the blockchain, enabling node operations, transaction management, and network testing.
Python
Blockchain
Cryptography
Flask
REST APIs
Distributed Systems
Python
Blockchain
Cryptography
Flask
REST APIs
Distributed Systems
Smart Contracts and Web3 Projects
Developed and deployed multiple Ethereum-based applications including Kickstarter, Lottery, and Inbox using Solidity smart contracts.
Built and tested decentralized applications integrating smart contract logic with Web3 interfaces and Node.js-based backend services.
Solidity
Ethereum
Smart Contracts
Web3.js
Node.js
Blockchain
Solidity
Ethereum
Smart Contracts
Web3.js
Node.js
Blockchain
Quora Question Pair Similarity
Built an NLP system to classify whether pairs of questions are semantically similar using advanced text representation and machine learning techniques.
Modeled the problem with a focus on high accuracy and interpretability, leveraging feature engineering and ensemble methods for duplicate detection.
Python
NLP
Machine Learning
Random Forest
Feature Engineering
Scikit-learn
Python
NLP
Machine Learning
Random Forest
Feature Engineering
Scikit-learn
Stack Overflow Tag Prediction
Developed a multi-label NLP model to predict relevant tags for Stack Overflow questions based on title and content.
Optimized for high precision and recall using text preprocessing, feature extraction, and machine learning techniques on large-scale datasets.
Python
NLP
Machine Learning
Multi-label Classification
Scikit-learn
Feature Engineering
Python
NLP
Machine Learning
Multi-label Classification
Scikit-learn
Feature Engineering
Distributed Cloud Systems and Scalable Computing
Implemented distributed systems concepts including task scheduling, resource management, and scalable service design for high-performance environments.
Built cloud-native components leveraging parallel processing, fault tolerance, and large-scale data processing inspired by real-world architectures.