Skip to content
View maroofiums's full-sized avatar
🎯
Focusing
🎯
Focusing
10 followers · 9 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report maroofiums

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
maroofiums/README.md

Typing SVG

Hi there, I'm Maroof

I am an AI/ML developer focused on building strong foundations in mathematics, backend systems, and applied machine learning. My goal is to understand how core concepts in math and computer science translate into real-world applications and to use that understanding to build practical, efficient, and scalable systems. I spend most of my time learning and strengthening fundamentals rather than rushing into advanced tools, because I believe strong basics lead to long-term growth. I am currently improving my skills in Python programming, data structures, and problem-solving while also studying key mathematical areas like linear algebra, probability, and calculus, which are essential for understanding machine learning models. Alongside this, I am learning backend development concepts such as APIs, databases, and system design to understand how full applications are built and deployed. In machine learning, I am exploring both theory and implementation by working on small projects, experimenting with models, and learning how training and evaluation processes work. My interest lies in connecting all these areas math, machine learning, and backend engineering to build complete, real-world AI systems. My long-term goal is to become a skilled AI engineer who can design, develop, and deploy intelligent solutions. I am continuously learning, practicing, and improving every day with consistency and discipline.

  • 🎓 Studying Software Engineering at MITI (expected graduation: Oct 2027)
  • 🔭 Currently building Velox and progressing through my ML roadmap
  • 🧠 Currently learning Computer Vision, DSA, MLOps, and Reinforcement Learning
  • 🌍 Based in Karachi, Pakistan
  • 💬 Ask me about building AI pipelines, RAG systems, and scalable FastAPI backends
  • 📫 Reach me at maroof96965@gmail.com
  • 🖥️ Portfolio maroofiums.vercel.app

📌 About Me

  • 🌱 I'm currently learning Machine Learning, Deep Learning, and System Design
  • 👯 I'm looking to collaborate on real-world AI/ML and FastAPI backend projects
  • 🤝 I'm looking for help with scalable ML systems and production-level deployment
  • 🚀 I enjoy building end-to-end AI systems from data to deployment

🧠 My Focus Areas

  • Machine Learning & Deep Learning
  • Backend Development (FastAPI)
  • MLOps & Model Deployment
  • Data Science & Analytics
  • Open Source Contribution

📊 GitHub Stats

📈 Contribution Activity

🔥 Streak Statistics

📅 Contribution Calendar

🔗 Connect With Me

Pinned Loading

  1. AI-Research-Assistant AI-Research-Assistant Public

    AI Research Assistant is a RAG system using FastAPI, LangChain, ChromaDB, and Mistral AI. It lets users upload PDFs, stores embeddings, retrieves relevant chunks via semantic search, and generates …

    Python

  2. A3-Attention A3-Attention Public

    Adaptive Transformer attention mechanism with learnable, input-conditioned activation for dynamic attention normalization in PyTorch.

    Jupyter Notebook

  3. AI-Learning-OS AI-Learning-OS Public

    Python

  4. CognifyAI CognifyAI Public

    Full-stack AI-powered code analysis platform that performs syntax validation, bug detection, security scanning, complexity analysis, optimization, and documentation generation using FastAPI and opt…

    Python

  5. HAR-Activity-Recognition HAR-Activity-Recognition Public

    A production-ready Human Activity Recognition (HAR) system built with PyTorch using a hybrid CNN-LSTM architecture to classify smartphone sensor data into six human activities. Features subject-wis…

    Python

  6. Movie-Recommender Movie-Recommender Public

    A production-ready deep learning movie recommendation system using Siamese Transformer Networks, contrastive learning, FAISS vector search, and FastAPI. Learns semantic movie embeddings for fast, s…

    Python