Junaid Ahmad Noor
Full-stack AI SaaS developer for scalable web apps
Ready for work
Junaid Ahmad is ready for their next project!
RAG Workspace — Multi-Tenant Document Q&A Platform
Built a full-stack retrieval-augmented generation (RAG) platform enabling teams to query uploaded documents with source-grounded, cited answers.
Designed FastAPI backend with JWT authentication, role-based access control (RBAC), and strict multi-tenant workspace isolation for multiple concurrent organisations.
Implemented semantic search using ChromaDB vector database alongside MongoDB, reducing document query response time significantly vs. keyword search.
Integrated multiple LLM backends including Ollama (self-hosted) and OpenAI-compatible APIs, enabling flexible model switching without code changes.
Tech: FastAPI, React, ChromaDB, MongoDB.
0
16
Nate
In this user can add the lecture link from you tube and get the video transcript
user can get the Key points from that lecture
user can get the summary from that lecture
user can get MCQs and did RAG based chat
1
25
InboxAI — AI Email Triage & Workflow Automation Platform
Built a full-stack Next.js automation platform that classifies Gmail messages by urgency using LLMpowered analysis and triggers downstream actions in Slack, Notion, and ClickUp via OAuth integrations.
Implemented multi-tenant organisation support with JWT-based authentication, secure cookie sessions, Zod input validation, and OAuth state protection across 4 third-party provider integrations.
Developed a configurable automation engine with a scheduled cron execution system, retry logic for transient API failures, and full run history and event logging for audit visibility.
Deployed on Railway with health check endpoints, environment-driven configuration via validated settings, and a modular project structure ready for CI integration.
Tech: Next.js, React, TypeScript, MongoDB, JWT, Google OAuth, Slack API, Notion API, ClickUp API, Tailwind CSS, Railway.
0
32
Built a full-stack SaaS platform enabling businesses to create branded, knowledge-backed chatbots with an embeddable JavaScript widget deployable on any website with a single script tag.
Engineered a complete RAG ingestion pipeline supporting PDFs, URLs, and raw text — chunking, embedding via FastEmbed, and storing dense and sparse vectors in Qdrant for hybrid semantic retrieval.
Designed multi-tenant system architecture with onboarding flows, bot CRUD, per-bot analytics dashboard (message events, top questions, routing breakdown), and an admin moderation panel.
Containerised the full application using Docker with a multi-stage build; deployed on Railway with a single-process SPA+API pattern and automated health check endpoints.
Tech: React, Vite, TypeScript, FastAPI, MongoDB, Qdrant, Groq, Docker, Railway, Tailwind CSS, shadcn/ui.
Link: https://dashbot-production-ff88.up.railway.app (https://dashbot-production-ff88.up.railway.app/)
0
43