Skip to content
View sunnynguyen-ai's full-sized avatar
🎯
Focusing
🎯
Focusing
  • San Jose
  • 19:57 (UTC -12:00)

Block or report sunnynguyen-ai

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
sunnynguyen-ai/README.md

Hi there! 👋 I'm Sunny Nguyen

🚀 Deep Learning Researcher | Large Language Models & Foundation Model Safety

🔭 Currently Working On

  • Mechanistic Interpretability: Building tools to understand how transformers process information and form internal representations
  • LLM Training Efficiency: Investigating novel architectures and optimization techniques for parameter-efficient language models
  • Foundation Model Safety: Developing evaluation frameworks and alignment techniques for safer, more reliable LLMs

🛠️ Tech Stack & Expertise

Core ML/AI:
PyTorch Transformers JAX DeepSpeed

LLM Specialized:
PEFT vLLM Accelerate TransformerLens

Research & MLOps:
WandB Docker Git Python

🎯 Featured Projects

Interactive interpretability tool for transformer models

  • Visualizes attention patterns across all layers for models up to 1.3B parameters
  • Interactive heatmaps showing token-to-token attention weights and head specialization
  • Impact: Helps researchers understand how LLMs process different text types
  • Features: Layer-wise analysis, attention head clustering, prompt comparison mode
  • Tech: PyTorch, Transformers, Streamlit, Plotly, NumPy

Explainable AI for financial applications

  • Processes 10M+ transactions with <50ms latency using ensemble models
  • SHAP-based explanations for regulatory compliance and model transparency
  • Performance: 35% reduction in false positives vs baseline systems
  • Tech: XGBoost, SHAP, Kafka, FastAPI, Redis

Deep learning for healthcare diagnostics

  • CNN ensemble for pneumonia detection achieving 94.2% accuracy on chest X-rays
  • Includes uncertainty quantification and confidence scoring for clinical decisions
  • Dataset: Trained on 5,856 chest X-ray images with data augmentation pipeline
  • Deployment: Streamlit web app with DICOM file support and batch processing
  • Tech: TensorFlow, Keras, OpenCV, Streamlit, Matplotlib

End-to-end ML pipeline for real estate valuation

  • Complete ML workflow from data collection to model deployment and monitoring
  • Feature engineering with 80+ variables including location, demographics, and market trends
  • Performance: Achieved MAE of $12,500 on California housing dataset (15% improvement)
  • Production: Flask API with automated retraining pipeline and A/B testing framework
  • Tech: scikit-learn, Flask, PostgreSQL, Docker, Pandas

📈 Current Learning Focus

  • Advanced transformer architectures (Mamba, Mixture of Experts)
  • Reinforcement Learning from Human Feedback (RLHF)
  • Constitutional AI and alignment techniques
  • MLOps best practices for large-scale model deployment

🎨 Fun Fact

When I'm not decoding neural networks, you'll find me capturing the beauty of nature through photography 📸 or building sustainable tech solutions for environmental challenges! 🌱


"Understanding intelligence—whether artificial or natural—requires building it piece by piece." - Personal Research Philosophy

Pinned Loading

  1. fraud-detection-system fraud-detection-system Public

    Real-time fraud detection system using ensemble ML models, featuring streaming data processing, explainable AI with SHAP, and production-ready deployment with FastAPI and Docker.

    Python 18 22

  2. house-price-prediction house-price-prediction Public

    End-to-end ML project predicting house prices using Python, scikit-learn, and Flask

    Python 4 3

  3. medical-image-classifier medical-image-classifier Public

    Deep learning model for pneumonia detection in chest X-rays using TensorFlow and Streamlit

    Python 17 17

  4. llm-attention-visualizer llm-attention-visualizer Public

    Interactive tool for analyzing attention patterns in transformer models with layer-wise visualizations, token importance scoring, and attention flow diagrams

    Python 18 17