I'm a Computer Science Honours student at Monash. I build tokenizers in Rust, distributed backends in Go, transformers in PyTorch. I'm particularly interested in agentic systems and distributed systems engineering. The matrix cube on the right is kinda cool, no?
01 · Grounded
Grounded indexes my PDFs, lecture slides, markdown notes, and thesis drafts. Ask it something and you get back the exact passage, with the file and page it came from.
I keep losing things in my own files. A paper I annotated weeks ago, a note I wrote for a past assignment, a half-finished paragraph of my thesis. I can feel the idea is in there somewhere, but finding it takes long enough that I usually give up and rewrite it.
The point is not to generate text. The point is to find the passage that is already there, and show me exactly where it came from.
Grounded is my attempt at fixing that. A local-first desktop app that indexes everything I study, read, or write, then hands back the passage and the page when I ask for it.
I am building it because I need it. My honours year is a pile of audio deepfake papers, scattered notes, and drafts I keep forgetting I wrote. Nothing I have tried retrieves at the level I want, so I am starting from the bottom: plain lexical search in Rust with Tantivy, SQLite for metadata, a Tauri shell on top. I plan to add semantic retrieval after the core is solid.
This is not another chat-with-your-PDF wrapper, a Zotero replacement, or a note app with an AI panel bolted on the side. Grounded only has to be a local index and a way to see the source, so Obsidian, Zotero, and my editor stay where they are.
02 · Projects
Six projects, ordered by how far down the stack I went. It starts with a Rust tokenizer, a Go banking core, and a PyTorch transformer; the rest are smaller things.
03 · Stack
Grouped by where each one sits in my stack. Every item below is something I use in shipped code or current research, not something I read about once.
04 · Education
I finished my undergrad in algorithms and data structures last year, and I'm in honours now, working on audio deepfake detection.
2026
Monash University · Melbourne, Australia
In progressHonours in partnership with the Australian Federal Police.
Synthetic audio turns up in fraud and impersonation calls more than people realise, and the ear alone is not enough to catch it. Detectors today tend to fall over once a clip is short, heavily compressed, or generated by a model they were never trained on. My thesis is a narrow question inside that mess: do discretized acoustic features give a detector more to work with than the usual continuous ones, both for spotting fakes and for locating the segment that was faked? The work runs the major benchmarks, leans on self-supervised speech encoders and tokenized audio, and compares representations head to head in one pipeline.
2022 to 2025
Monash University · Melbourne, Australia
Graduated December 2025
