Skip to content
View munimx's full-sized avatar
😎
😎
1 follower · 0 following

Highlights

  • Pro

Block or report munimx

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
munimx/README.md
Munim Ahmad - Full-Stack AI Engineer typing

About Me

Full-Stack AI Engineer with expertise in building production-ready AI applications
from model development to deployment. I specialize in RAG systems,
LLM optimization, and scalable backend architecture.

Tech Stack

🤖 AI / ML

PyTorch
PYTORCH		 TensorFlow
TENSORFLOW		 Scikit-learn
SKLEARN		 HuggingFace
HUGGINGFACE		 LangChain
LANGCHAIN		 OpenAI
OPENAI
Pinecone
PINECONE		 ChromaDB
CHROMADB		 MLflow
MLFLOW		 W&B
W&B		 Anthropic
ANTHROPIC		 LlamaIndex
LLAMAINDEX
FAISS
FAISS		 Weaviate
WEAVIATE		 n8n
N8N		 Zapier
ZAPIER

🌐 Full-Stack

React
REACT		 Next.js
NEXT.JS		 TypeScript
TYPESCRIPT		 Node.js
NODE.JS		 Express
EXPRESS		 Electron
ELECTRON
Flask
FLASK		 FastAPI
FASTAPI		 .NET
.NET		 GraphQL
GRAPHQL		 Python
PYTHON		 JavaScript
JAVASCRIPT

🗄️ Databases

PostgreSQL
POSTGRESQL		 MySQL
MYSQL		 MongoDB
MONGODB		 Firebase
FIREBASE		 DynamoDB
DYNAMODB		 Redis
REDIS
SQLite
SQLITE		 Weaviate
WEAVIATE		 Supabase
SUPABASE

☁️ Cloud & DevOps

AWS
AWS		 Docker
DOCKER		 Kubernetes
KUBERNETES		 GitHub Actions
ACTIONS		 GitLab
GITLAB CI		 Prometheus
PROMETHEUS		 Grafana
GRAFANA

🔧 Tools & Auth

Git
GIT		 Postman
POSTMAN		 Jest
JEST		 RabbitMQ
RABBITMQ		 Auth0
AUTH0		 Okta
OKTA
Celery
CELERY		 Pytest
PYTEST		 VS Code
VS CODE

Featured Projects

🔮 recallm

Semantic LLM Cache

Semantic cache layer for LLM APIs — embeds prompts locally, finds near-matches, and skips redundant LLM calls to slash costs and latency.

🤖 DocuChat

Cross-Platform AI PDF Assistant

Desktop app for intelligent Q&A over PDFs with RAG architecture, multiple LLM support (OpenAI, Claude, local models), and real-time chat with source citations.

⚙️ LLM Inference Optimization Engine

Production-Grade LLM Orchestration

Intelligent optimization layer on top of Ollama with smart batching, speculative decoding (2-4x speedup), multi-level quantization, and pluggable scheduling policies (FCFS, SJF, Priority, Token-based).

📝 Folio

Offline-First Task Manager

Beautiful, fast, offline-capable task manager PWA with optional push notifications and a smooth cross-device experience.

📋 Folio

Offline-First Todo App

Beautiful, fast, offline-capable task manager with optional Web Push notifications, service worker caching, and a responsive TypeScript frontend.

⚡ Real-time Streaming System

Kafka + Chrome Extension

Real-time webpage screenshot streaming using Apache Kafka and a custom Chrome extension for live data capture.

Highlights

🤖 AI/ML       RAG Systems • LLM Fine-tuning (LoRA/QLoRA) • Vector DBs (FAISS, Weaviate) • Prompt Engineering • n8n/Zapier Automation
🌐 Full-Stack  React • Next.js • Node.js • .NET • Electron • FastAPI • WebSockets • gRPC
☁️ Cloud       AWS (EC2, S3, Lambda, SageMaker, ECS) • Docker • Kubernetes • CI/CD
📊 Data        PostgreSQL • MongoDB • Redis • SQLite • Pinecone • ChromaDB • Weaviate

Let's Connect

I'm always open to collaborating on AI-powered applications and full-stack projects!

Show some by some repositories!

Pinned Loading

  1. DocuChat DocuChat Public

    Cross-Platform AI PDF Assistant - Chat with your PDF documents using AI

    TypeScript 1

  2. recallm recallm Public

    Semantic cache layer for LLM APIs — embed prompts locally, find near-matches, skip redundant LLM calls.

    Python 2

  3. LLM-Inference-Optimization-Engine LLM-Inference-Optimization-Engine Public archive

    [DEPRECATED]

    Python

  4. Folio Folio Public

    A beautiful, fast, offline-capable todo app with optional push notifications.

    TypeScript

  5. JSON-to-UseCase-Diagram JSON-to-UseCase-Diagram Public

    Web app to convert JSON use case data into formatted, Word-compatible HTML tables. Supports single or multiple objects, automatic table generation, and clipboard copy for easy documentation.

    JavaScript 1

  6. Real-time-Webpage-Screenshot-Streaming-System Real-time-Webpage-Screenshot-Streaming-System Public

    Demo for Kafka by streaming screenshots of trading-view chart through a chrome extension

    JavaScript 1