Skip to content
View Snowyyxx's full-sized avatar
5 followers · 0 following

Block or report Snowyyxx

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
Snowyyxx/README.md

Aditya Jain

Machine Learning • Full-Stack
📧 Email |

🧠 AI Engineer with a focus on building interpretable, production-grade ML systems
⚙️ Leveraging Vision Transformers, Wavelet Analysis, XAI, and LangChain to solve real-world problems
🔬 Architecting pipelines that combine deep learning, structured logic, and scalable infrastructure

🧠 Flagship Projects

  • Brain Tumor Classification
    96.4% accuracy on enhanced MRI data using ResNet + Vision Transformers.
    Integrated SHAP + ScoreCAM for pixel-level tumor explainability.

  • Welding Parameter Prediction
    Multi-output regression pipeline using deep autoencoders + SHAP
    Achieved R² = 0.93 | 5-Fold CV | Ensemble stacked model

  • 1v1 DSA Duel Platform (Current)
    Real-time competitive coding arena using Django Channels, WebSockets, and live judge sync.

  • SmartFormFiller (Open Source)
    Chrome extension to parse resumes, extract metadata, and auto-fill Google Forms.
    PDF parsing + DOM mutation + Chrome Storage APIs.

  • Neural Network in C++ (from scratch)
    Custom backprop, weight updates, and training loop in raw C++ OOP — no libraries used.

  • OsttraGPT (Internship)
    Enterprise-grade GenAI assistant using LangChain, Tesseract OCR, and FastAPI.
    Reduced QA overhead by 10+ hours/week via automation of metadata extraction.

⚒️ Core Stack

Languages: Python, C++, JavaScript
Frameworks: PyTorch, FastAPI, Django, React
ML/AI: Vision Transformers, SHAP, LangChain, OCR, Generative AI
DevOps: Docker, Git, SQLite, Chrome Extensions, WebSockets

🏁 Highlights

  • Solved 400+ DSA problems across LeetCode
  • Delivered real-world ML pipelines used in industry & open source
  • Obsessed with performance, explainability, and clean system architecture

Pinned Loading

  1. Food-Recipe-Creator Food-Recipe-Creator Public

    recognizes indian food limited to certain categories and creates a recipe for it using chatgpt

    Jupyter Notebook

  2. Fast-Food-Restaurant-Order-Management-System Fast-Food-Restaurant-Order-Management-System Public

    multi-threaded order management system for a fast-food restaurant using C++ and SQLite. Implemented order placement and processing ensuring thread safety with mutexes and atomic variables

    C++

  3. ChatBotUsingLangchain ChatBotUsingLangchain Public

    using langchain, i create a chatbot where you can talk with your pdf file and ask it questions

    Jupyter Notebook

  4. Tweet-Emotion-Classifier Tweet-Emotion-Classifier Public

    classifies the tweet into 6 categories of emotions. used transfer learning.

    Jupyter Notebook

  5. Trading_Platform Trading_Platform Public

    simulated a trading platform where stocks are being sold and bought parralely. records are being mantained in a sqlite database. used threads and mutex to ensure mutual exclusion of processes .

    C++

  6. Ice-Cream-E-Store Ice-Cream-E-Store Public

    This project is a Django-based web application designed to simulate an online ice cream shop. It demonstrates the use of Django for backend development and Bootstrap for frontend styling, showcasin…

    HTML 1