Featured Projects

Browse the AI/ML projects shown below and explore the complete code portfolio on GitHub.

View all repositories and source code on github.com/ImranRafique847.

AI Shopping Assistant

AI-Based Shopping Assistant

Intelligent eBay fashion shopping assistant powered by Corrective RAG (CRAG) on AWS. Users search 18,992 real products using natural language — the AI rewrites queries, performs FAISS semantic search, filters by price/condition, and generates honest responses with product cards.

PythonFastAPIFAISSAWS BedrockTitan EmbeddingsNova MicroDockerElastic BeanstalkS3ECR
Car Damage Detection

AI Car Damage Classification

End-to-end deep learning system classifying car damage severity (minor, moderate, severe, no damage) using EfficientNetB3 transfer learning with 2-phase training. Deployed live on AWS Lambda via Docker container with API Gateway.

PythonTensorFlowEfficientNetB3Transfer LearningFlaskAWS LambdaDockerECRAPI Gateway
AI Data Visualization Agent

AI Agent for Data Visualization

AI-powered data analysis agent using Claude via AWS Bedrock that converts natural language queries into automated visualizations. Upload any dataset and ask questions — the agent generates charts and insights automatically.

PythonStreamlitAWS BedrockClaudePandasMatplotlibSeaborn
Personal AI Agent

Personal AI Agent — MCP Server

Conversational AI assistant that controls Gmail, Google Drive, and Google Calendar through natural language. Built with Model Context Protocol (MCP), Claude Haiku via AWS Bedrock, FAISS vector memory, and multi-agent architecture.

PythonMCPAWS BedrockClaudeFastAPIFAISSGoogle APIsMulti-Agent
Flight Booking Agent

Flight Booking Conversational Agent

Google Cloud Dialogflow CX conversational agent for flight booking. Handles intent recognition, entity extraction (cities, dates, passenger name), confirmation flows, and conditional routing for smooth multi-turn conversations.

Dialogflow CXGoogle CloudConversational AINLPIntent Recognition
Health Chatbot

Health Chatbot

Python-based health chatbot application providing intelligent health-related conversational responses using NLP techniques and AI-powered backend processing.

PythonNLPChatbot
Research Paper Analyzer

Research Paper Analyzer Chatbot

RAG-based chatbot that analyzes research papers and provides intelligent Q&A over academic documents. Built with a RAG pipeline for document-based question answering.

PythonRAGLangChainStreamlit
Sales Dashboard

Sales Dashboard

Interactive sales analytics dashboard built with Power BI on SuperStore sales data, featuring visual reports, trend analysis, and business intelligence insights.

Power BIData VisualizationAnalyticsCSV
Car Price Prediction

Car Price Prediction

Machine learning regression model predicting car prices using vehicle features. Includes Jupyter Notebook for EDA and model training, plus a Streamlit web app for real-time predictions.

PythonJupyter NotebookScikit-learnStreamlitRegression

Professional Experience

AI/ML Engineer Intern

Salaar Technologies • Onsite • November 2025 – Present

  • Developed an AI chatbot combining rule-based logic and RAG for fast, context-aware responses, processing 140+ PDFs
  • Implemented intelligent document chunking, vector similarity search, and hybrid query handling
  • Built FastAPI backend with a single /chat endpoint for scalable deployment
  • Integrated Google Sheets API to log user queries and chatbot responses in real-time
  • Optimized LLM usage with controlled generation for faster, cost-effective answers

AWS Community Builder (AI/ML Track)

Amazon Web Services • March 2026 – Present

  • Selected into a global program of technical professionals for demonstrating proficiency in Generative AI and Cloud Architecture
  • Actively contributing to the AWS ecosystem by developing RAG-based applications and Agentic workflows using Amazon Bedrock
  • Granted early access to pre-release AWS services and direct mentorship from AWS Product Teams

Career-Prep Fellow

Amal Academy (Stanford-funded) • April 2025 – May 2025

  • Selected from 4,500+ applicants for a rigorous 3-month fellowship
  • Invested 150+ hours building skills in communication, leadership, and problem-solving

Data Science Intern

Certura • April 2025 – May 2025

  • Built a regression model on 95,845 flight records to predict passenger volume per route (R² = 0.87)
  • Managed end-to-end ETL with EDA, data cleaning, transformation, and feature engineering