Projects

Complete website development and AI integration for SightedVision Ltd, a UK-based social work consultancy specializing in SEND services. Delivered a modern, accessible platform with AI-powered features to enhance their professional education and consultancy services. Key Contributions: - Full-stack website development with Next.js and TypeScript - AI chatbot integration for client support and consultation booking - Mobile-responsive design optimized for accessibility - SEO optimization and performance enhancements - Integration with existing business workflows

Founded and developed HectorLabs, an AI consulting startup platform that helps businesses integrate AI technology into their workforce. Built a comprehensive platform showcasing AI implementation services, client success stories, and consultation booking system. Key Features: - AI consulting service showcase and booking system - Client portfolio and case studies presentation - AI readiness assessment tools - Lead generation and client management system - Modern, conversion-optimized design

An interactive machine learning playground that demonstrates classic classification algorithms on popular datasets. Explore KNN, SVM, Random Forest, and more with real-time visualization and performance metrics. Key Features: - Multiple ML algorithms (KNN, SVM, Random Forest) - Popular datasets (Iris, Breast Cancer, Wine, Diabetes) - Real-time model training and evaluation - Interactive parameter tuning and visualization

An end-to-end serverless RAG (Retrieval-Augmented Generation) system demonstrating production-grade GenAI architecture on AWS. Key Features: - Designed an end-to-end serverless RAG system using AWS Bedrock, API Gateway, and Lambda with stateless inference - Implemented Amazon Titan Text Embeddings v2 (1024-dim float vectors) stored in OpenSearch Serverless vector engine, with S3-backed knowledge base ingestion - Frontend built using HTML/CSS/JavaScript and hosted on AWS Amplify, demonstrating a cost-efficient GenAI production architecture

A complete, enterprise-grade MLOps solution for deploying machine learning models at scale. Demonstrates the full lifecycle from model training to cloud deployment. Key Features: - Production-ready FastAPI-based inference service with Random Forest classifier (96-100% accuracy) - Dockerized deployment with pre-built image available on Docker Hub - Kubernetes-ready with Minikube integration for local testing - AWS ECR + EKS production deployment workflow - Complete CI/CD pipeline integration ready - Scalable, secure, and production-tested architecture

A fine-tuned language model built on facebook/opt-350m optimized for dialogue-style Q&A on political and philosophical topics. The model was trained on a custom dataset of question-answer pairs focusing on Marxist theory, history, and related political contexts.

A Python-based recommendation engine that suggests movies based on user preferences using collaborative filtering and machine learning algorithms.

A beautifully designed Todo app that showcases fundamental programming paradigms. Building a Todo application demonstrates core principles of state management, user interactions, and data persistence that are essential for any developer to master.