ExtremeMind Studio

Overview

A cutting-edge AI-powered interview platform built with Azure cloud-native architecture, featuring GPU-accelerated Azure GPT-OSS inference, real-time virtual human interaction, and enterprise-grade speech processing capabilities.

Core Features

• AI-Powered Interview Engine – Real-time question generation and scoring using Azure GPT-OSS with GPU acceleration, enabling adaptive follow-up questions and intelligent evaluation workflows
• Photorealistic Virtual Interviewers – D-ID Clips Streams integration with WebRTC for ultra-low latency video streaming, providing life-like avatars with synchronized speech and expressions
• Advanced Speech Processing – Azure Cognitive Services integration for continuous Speech-to-Text (STT) with silence detection, and Text-to-Speech (TTS) enhanced with viseme-driven facial animation
• Flexible Multi-LLM Architecture – Supports GPT-OSS, vLLM, Ollama, and Mock models with automated load balancing and fallback mechanisms for maximum reliability
• Real-Time Communication Layer – WebRTC-based peer connection with ICE/STUN/TURN support, ensuring seamless interviewer–candidate interaction across diverse network conditions
• Cloud-Native Scalability – Fully containerized architecture with .NET 8 Web API, React + TypeScript frontend, and Azure-managed services for enterprise-grade availability and performance

Overview

A full-stack data visualisation dashboard for retail procurement, sales, and inventory analysis. Users upload Excel files, the system ingests and computes daily metrics (including Procurement Amount and Sales Amount), and renders interactive multi-product charts with detail-on-demand. Secure login, multi-dataset management, and AI-assisted insights (Gemini) help users quickly explore trends. The app is built with a modern TypeScript/React/Next.js stack and deployed to Azure App Service with CI/CD, backed by Azure Database for PostgreSQL.

Core Features

• Transactional Data Processing – Prisma ORM with database transactions ensuring ACID compliance - complete rollback on any processing failure, preventing partial data states
• Next.js Middleware Protection – Route-level access control with automatic redirects, token validation on every request, and seamless session management across page/API boundaries
• Real-Time Dataset Analytics – Computed metadata including record counts, date ranges, and product statistics served via optimized API endpoints
• Google Gemini 1.5-Flash Integration – Advanced prompt engineering with structured JSON data feeds, enabling natural language queries like "Which product had the highest sales growth?"
• GitHub Actions CI/CD Pipeline – Automated testing, building, and deployment with Azure OIDC authentication for secure cloud resource access
• Azure App Service Deployment – Containerized Next.js application with environment-based configuration management and automatic scaling capabilities
• Azure Database for PostgreSQL – Managed relational database with connection pooling, automated backups, and high availability ensuring 99.9% uptime for production workloads
• Strict Type Safety – Full TypeScript implementation with discriminated unions, mapped types, and generic constraints ensuring compile-time error prevention

Overview

A full‑stack web application that streamlines exam grading through AI‑assisted answer evaluation, configurable marking rules, and role‑based access control, featuring manual review tools, Excel data integration, and detailed reporting for admins, test developers, and markers. The system is built with modern cloud-native architecture and deployed on AWS for high availability and scalability.

Core Features

• Automated Scoring – Intelligent evaluation with flexible marking rules (case, punctuation, spelling, grammar)
• Role‑Based Access – Dedicated dashboards for Admins, Test Developers, and Markers
• Manual Review – Flagged answers for human validation and scoring
• Excel Integration – Import student responses and export scored results
• Real‑Time Reporting – Live progress tracking and performance analytics
• Advanced Linguistic Checks – Spelling & grammar analysis for accurate scoring
• Cloud‑Native Architecture – Built for AWS deployment with auto-scaling capabilities