Skip to content
View AbhimanthaW's full-sized avatar

Block or report AbhimanthaW

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
AbhimanthaW/README.md
┌─ A/W ────────────────────────────────────────────┐
│                                                 │
│  ABHIMANTHA WIJESUNDARA                         │
│  founder · developer · researcher               │
│                                                 │
│  build products · understand systems            │
└─────────────────────────────────────────────────┘

Founder at Arizonia Phoenix.
I build software, research intelligent systems, and study the computer science and mathematics underneath them.

AI · SOFTWARE ENGINEERING · COMPUTER SCIENCE · MATHEMATICS · ROBOTICS


01 · BUILD

Arizonia Phoenix

Company / product ecosystem

An early-stage technology company where I take ideas through product thinking, architecture, implementation, and iteration. Current work sits around AI, SaaS, and software products built to solve concrete problems.

The interesting part is not adding AI to everything. It is building systems where the technology earns its place.

02 · INVESTIGATE

Project Athena

Independent research / computer science + mathematics

A long-term research track around AI, language models, information theory, computation, and mathematical reasoning. I learn by rebuilding systems from first principles, running experiments, and documenting what changes their behaviour.

athena-tinylm
A small, interpretable transformer language model built substantially from first principles to study how architecture, data, tokenisation, and compute shape learned language behaviour.

03 · ENGINEER

I work across the stack when the problem requires it.

Python · TypeScript · Dart · C
React · Flutter · Node.js · Firebase

The tools change. The recurring questions do not: How does it work? Where does it fail? What is the simplest architecture that remains correct?

Beyond software

Physics and mathematics keep pulling me toward first principles. Away from code: guitar, chess, and the occasional experiment that started with “I wonder what happens if…”


Currently building at the intersection of products, intelligent systems, and fundamental ideas.

Popular repositories Loading

  1. AbhimanthaW AbhimanthaW Public

    1

  2. athena-tinyllm athena-tinyllm Public

    A small, interpretable transformer language model built substantially from first principles, used to investigate how architecture, data, tokenisation, and computational budget affect learned langua…

    Jupyter Notebook 1

  3. AZ-900-prep AZ-900-prep Public

    My complete Microsoft Azure Fundamentals (AZ-900) study notes, labs, diagrams, flashcards, and revision material.

    1

  4. athena-context-sparsity athena-context-sparsity Public

    Research project investigating whether training-only context sparsity can predict the marginal held-out benefit of increasing n-gram order.

    Python 1

  5. robotics-refresh robotics-refresh Public

  6. cs50x cs50x Public

    Harvard's CS50x: Introduction to Computer Science

    1