Skip to content
View duytrangiale's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report duytrangiale

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
duytrangiale/README.md

Hi, I'm Duy Le 👋

PhD · Computational Modelling & Deep Learning · CSIRO

profile views

I build neural network surrogates for granular material simulation and physics-informed ML systems and I'm increasingly focused on applied AI/agentic engineering. Currently exploring industry roles in ML/AI engineering, robotics, and computational modelling across Australia.


📚 Education

  • 👨‍🎓 PhD in Engineering — Federation University Australia (with CSIRO, fully RTP-funded) Thesis: "Accelerated Surrogate Modelling of Granular Materials using Artificial Neural Networks"
  • 👨‍🎓 Master of Engineering, Mechatronics (GPA: 6.2/7.0) — Australian National University
  • 👨‍🎓 Bachelor of Engineering, Mechatronics — Ho Chi Minh City University of Technology, Vietnam

✍️ Research Areas

  • Deep Learning & Neural Networks
  • Discrete Element Method (DEM) & Surrogate Modelling
  • Physics-Informed Neural Networks
  • Computational Modelling & Simulation
  • Mechatronics Design & Embedded Systems

🚀 Side Projects

Project Description
simple_notebooklm A document-grounded RAG learning assistant inspired by NotebookLM — upload PDFs, get grounded Q&A, summaries, quizzes, and flashcards with source citations.
urbancool_melbourne (demo) ML dashboard predicting urban heat vulnerability across Greater Melbourne from a Random Forest model (R² = 0.57): FastAPI backend, interactive SHAP explanations, and a live green-infrastructure what-if simulator.
eco_risk_au Geospatial + LLM ecosystem climate-risk platform for Victoria, Australia: PostGIS ETL pipeline computing a composite climate risk score per vegetation patch, a LangGraph + Gemini RAG pipeline extracting structured risk data from real IUCN Red List of Ecosystems documents, and a React + Leaflet dashboard.

💻 Tech Stack

AI / ML

Python PyTorch TensorFlow SciPy Pandas LangChain

Systems / Infra

FastAPI Docker Kubernetes ROS2 Qdrant

📊 GitHub Stats


Open to ML/AI engineering, robotics, and computational modelling roles in Australia — feel free to reach out!

Pinned Loading

  1. eco_risk_au eco_risk_au Public

    A Geospatial & LLM Ecosystem Risk Intelligence Platform

    Python

  2. urbancool_melbourne urbancool_melbourne Public

    Machine Learning - Powered Urban Heat Vulnerability Mapping

    Jupyter Notebook

  3. simple_notebooklm simple_notebooklm Public

    A document-grounded RAG (Retrieval-Augmented Generation) learning assistant inspired by Google's NotebookLM — upload PDFs and get grounded Q&A, summaries, quizzes, and flashcards, all with source c…

    Python

  4. HapticExoskeleton HapticExoskeleton Public

    A simulation framework and controller design for virtual reality exoskeleton

    C 1

  5. JavaBoardGame JavaBoardGame Public

    Mini Board Game created by Java and JavaFX

    Java

  6. MorseCodeRecognition MorseCodeRecognition Public

    This project implements the Morse code recognition device using the FPGA development board

    Verilog