Skip to content
View ryannduma's full-sized avatar
🦾
training ...
🦾
training ...

Highlights

  • Pro

Block or report ryannduma

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
ryannduma/README.md

Hello World 👋

I'm Ry — a Beacon Scholar born and raised in Nairobi, Kenya 🇰🇪, studying Materials Science & Engineering at Imperial College London.

My work explores how AI and machine learning can accelerate understanding and discovery in chemistry and materials science. I build tools like Crystalyse (multi-tool agentic materials design), Sky (synthesis exploration agent), and SMACT (chemical heuristics and property prediction toolkit).

My work is guided by an interest in the philosophy of science and interpretability, with a focus on how reasoning systems can solve pressing commercial and scientific challenges.

I am actively exploring opportunities where I can apply my skills to solve impactful problems. I am open to discussing roles in technical research, engineering, and consulting, as well as compelling PhD and Masters programs.

Side Notes

📜 Currently reading A Brief History of Intelligence (Max Bennett) and exploring Chris Olah’s interpretability work.
👯 Always open to collaborations on interpretability, agentic AI systems, and computational materials design.
🌱 Outside the lab, I’m catching up on Attack on Titan and finally playing Elden Ring.
📝 Writing: Substack · Thinklog
📫 Reach me via Email or LinkedIn

that's all, live well!

image

xkcd: Game Theory / #601 - remember: not everything yields to tidy optimisation—some "games" are worth playing precisely because the pay-offs are emotional, fuzzy, and shared


This README was last updated: Friday 10th October 2025, 7:30pm (UK Time)

Pinned Loading

  1. WMD-group/SMACT WMD-group/SMACT Public

    Python package to aid materials design and informatics

    Python 125 28

  2. materialsinformatics materialsinformatics Public

    SMACT Advanced Practical

    Jupyter Notebook 6 2

  3. hspark1212/synthesis-agent hspark1212/synthesis-agent Public

    2025 LLM Hackathon for Applications in Materials and Chemistry

    Python 19

  4. hspark1212/MatSX hspark1212/MatSX Public

    Materials Similarity Explorer (2025-KRICT-ChemDX-Hackathon)

    Python 3

  5. SignSpeak SignSpeak Public

    A Bilingual Sign Language and Speech Translator

    1

  6. learningvision learningvision Public

    Speed learning OpenCV, and Mediapipe tutorials - might also add projects/workdone from cs231n course here

    Python