Skip to content
View changzhiai's full-sized avatar

Block or report changzhiai

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.

Content in all repositories owned by your account will be closed.
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
changzhiai/README.md

Changzhi Ai, PhD

🎓 About Me (Open to work)

I am a Postdoctoral Researcher at Stanford University & SLAC (Menlo Park, CA), working at the intersection of Machine Learning and Chemistry. I earned my PhD from the Technical University of Denmark (DTU) in 2023.

  • 🤖 Building Agentic AI for Science — LLM agents that automate scientific workflows.
  • 📚 Interested in developing machine learning models for materials.
  • 💡 Enjoy applying ML/AI techniques to scientific and engineering problems.
  • 🔬 Expertise in ML/AI, global optimization, heterogeneous catalysis, reaction kinetics, and data-driven modelling.

⚛️ Developed Scientific Software

  • IANN — an equivariant InterAtomic Neural Network potential framework (Documentation)
  • AdsNet — a message-passing graph neural network for adsorption
  • PCAT — a Practical CATalysis toolkit
  • AlphaScheme — an alpha model for binding energy (private)

🔬 Research Highlights

🧠 Training and Courses

📱 Developed Cross-Platform Apps (Web / iOS / Android / Chrome)

🧩 Developed Chrome Extensions

🛠️ Skills & Tools

Skills Tools / Libraries
Programming Python, C++ (also HTML, CSS, JavaScript, TypeScript, PHP, Java)
ML / Data PyTorch, scikit-learn, numpy, pandas, MySQL
Agentic AI RAG, LangChain, LangGraph, LLM deployment, Skills, MCP
Scientific / Modeling DFT (VASP, GPAW), molecular dynamics (LAMMPS), Monte Carlo, microkinetic modeling, kinetic Monte Carlo
ML potentials FastPot, PaiNN, NequIP, MACE, EquiformerV2, AMP, N2P2
Global optimization Multitasking genetic algorithm, simulated annealing, minima hopping
Materials tools ASE (Atomic Simulation Environment), Pymatgen
DevOps & Tools Git, GitHub, Jupyter, Docker
Visualization Matplotlib, Seaborn, Plotly

Pinned Loading

  1. IANN IANN Public

    IANN (InterAtomic Neural Network) framework is an equivariant interatomic neural network potential framework package

    Python 18 1

  2. pcat pcat Public

    Practical CAtalysis Toolkit

    Python 1

  3. claude-code-patch claude-code-patch Public

    Make the leaked Claude Code runnable with unified local model support.

    TypeScript 13 4

  4. MachineLearning MachineLearning Public

    Machine learning exercise

    Python

  5. DeepLearning DeepLearning Public

    Deep learning course

    Jupyter Notebook

  6. cuEquivariance cuEquivariance Public

    Forked from NVIDIA/cuEquivariance

    cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural n…

    Python