Skip to content
View Ankur-krGarg's full-sized avatar

Block or report Ankur-krGarg

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
Ankur-krGarg/README.md

About me 👋

Hello! I’m Ankur Kumar Garg, a self-taught AI & Machine Learning Developer with strong hands-on experience building intelligent systems using Python, LLMs, and knowledge graphs.

Despite having no formal degree in this field, I’ve learned everything through practice, real-world problem-solving, and countless hours with docs, repos, and experiments.

🔧 What I work with:

  • Languages & Tools: Python, SQL, LangChain, LangGraph, FastAPI
  • AI & ML: LLM integration (OpenAI, HuggingFace), Transformers (Encoder-Decoder), Fine-tuning, RAG, Chatbots
  • Data Systems: Neo4j (Graph DB), DeepLake, vector stores (FAISS, Qdrant), Pandas, NumPy
  • Architecture & Projects: Multi-agent pipelines, Knowledge-Graph based reasoning, custom scriptable modules
  • Platforms: Google Colab, VS Code

📦 I’ve built:

  • AI-native pipelines for industrial intelligence
  • Credit Card Fraud Detection systems
  • XLRE ETF Analysis with PCA, SVD, and time-series modeling
  • Multi-agent RAG systems using LangGraph

🧠 I learn by doing — not by memorizing syntax, but by reading documentation, breaking systems, and building them again from scratch.

🎯 My goal: To work remotely with teams or clients who value curiosity, fast learning, and clean, scalable AI solutions.


📫 Feel free to connect — I'm always open to challenging freelance or remote roles in AI/ML and backend engineering.

Popular repositories Loading

  1. Fraud-Detection Fraud-Detection Public

    Detect fraudulent credit card transactions using ML. Includes data preprocessing, modeling, and results visualization

    Jupyter Notebook

  2. Predict-Stroke Predict-Stroke Public

    Predicting stroke risk using real health data and ML classifiers like Random Forest and XGBoost.

    Jupyter Notebook

  3. Credit-Risk Credit-Risk Public

    Predict credit risk using machine learning (LogReg, Random Forest). Built clean pipeline with EDA, modeling, and visualizations.

    Jupyter Notebook

  4. NewsArticleSummarizer NewsArticleSummarizer Public

    Summarizes news articles using LLMs and extractive-abstractive techniques via Hugging Face models.

    Jupyter Notebook

  5. ChatBot ChatBot Public

    Transformer-based chatbot demo using Hugging Face's conversational models

    Python 1

  6. AutonomusAgent AutonomusAgent Public

    Fully autonomous AI agent that performs multi-step reasoning, tool selection, and task execution using LLMs and LangChain.

    Jupyter Notebook