Skip to content
View khang3004's full-sized avatar
🌴
On vacation
🌴
On vacation

Highlights

  • Pro

Block or report khang3004

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
khang3004/README.md

Hi there, I'm Khang Nguyen (KhangDS) 🚀

Typing SVG

I specialize in architecting scalable Machine Learning pipelines and orchestrating multi-agent systems. My current focus is bridging the gap between rigorous academic research (Knowledge Representation & NLP) and production-ready Agentic AI. Currently, I'm deeply invested in enhancing LLM reasoning capabilities for complex structured data tasks.

LinkedIn Email YouTube

Khang's Trophies


Working On What I'm Currently Working On

  • 🎓 Pursuing a Master of Science in Data Science at University of Science (HCMUS).
  • 🧠 Developing AgentSQL: A multi-agent framework for robust Text-to-SQL generation and autonomous schema exploration.
  • 📊 Building DataAnalysis Agents that leverage complex workflows for automated insights and visualization.
  • 🧪 Researching GMM-based imputation techniques for handling missing data in high-dimensional datasets.
  • ⚙️ Optimizing MLOps with MLflow, Ray, and Amazon S3 for distributed training and experiment tracking.
  • Beyond the screen: A huge fan of FC Barcelona, Lionel Messi, and unwinding with Vietnamese Rap & V-Pop.

🛠️ Tech Stack & Arsenal

Languages & Frameworks

Python Java JavaScript R Swift FastAPI Streamlit Xcode

Data Science & Machine Learning

PyTorch HuggingFace Scikit-learn ONNX Pandas NumPy OpenCV Seaborn vLLM Metal Performance Shaders

Agentic AI & Orchestration

LangGraph LangChain LangSmith Groq MCP A2A Protocol

Databases & Data Engineering

PostgreSQL MySQL MongoDB Neo4j SQLite Redis Chroma Milvus Cassandra Apache Spark

MLOps & Workflow

MLflow Ray Amazon S3 Docker Git RabbitMQ Linux ngrok


Analytics GitHub Analytics

GitHub Stats GitHub Streak

Top Languages Activity Graph


🏆 Featured Architectures & Projects

Pinned Loading

  1. AgentSQL-Asym AgentSQL-Asym Public

    Production-grade Asymmetric Multi-Agent Text-to-SQL on BIRD-SQL. Offline CHESS/FAISS pruning + MCI-SQL enrichment feed ≤3 Groq API calls: gpt-oss-120b generator · llama-4-scout reflector · gpt-oss-…

    Python 2

  2. comprehensive-OCR comprehensive-OCR Public

    Python 1

  3. RAG_Chatbot_Underdogs RAG_Chatbot_Underdogs Public

    Python

  4. artist-revenue-management-project artist-revenue-management-project Public

    An end‑to‑end artist revenue management platform for the modern music industry, designed to help labels, managers, and independent artists track and optimize their earnings across catalogs and chan…

    Swift 1

  5. DataAnalysis_Agent DataAnalysis_Agent Public

    An agentic AI system for conversational data analysis. Upload any CSV, query your data in natural language, and receive instant insights, auto-generated visualizations, and executable Python code —…

    Jupyter Notebook

  6. LLMs-from-scratch LLMs-from-scratch Public

    Forked from rasbt/LLMs-from-scratch

    Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

    Jupyter Notebook