Work
Things I've built that are real
A live co-founded product, a client system in production, and self-initiated projects with metrics I can defend. Every one framed as evidence, not a pitch.
Flagship — live product & client system
bydhome — a real-estate marketplace, from zero to live
A live, co-founded property marketplace I helped take from a hard problem to something real people use. Equity partner; I own the AI and a good part of the product.
TriCab RFQ parser — unstructured quotes, made structured
A production AI system inside a cable manufacturer that turns unstructured request-for-quote input into structured, quotable data. Client work — shown as workflow and architecture only, no company data.
Projects — self-initiated, metric-backed
Property Search NLP Parser — natural-language search that pays for itself
A natural-language property search that replicates realestate.com.au's beta NL search, using hybrid routing to cut LLM cost ~90% while improving location accuracy. Built to target an REA machine-learning role.
Invoice Extraction & Analytics Dashboard — messy invoices to clean data
An end-to-end pipeline that turns unstructured invoices into validated, structured data with an analytics dashboard on top — cutting manual processing time ~80%.
Experience
ML Engineer Intern
Built evaluation frameworks for language-model outputs across 20k+ samples, with deployment to the HuggingFace Hub and cloud.
IT & Automation Intern
Automated internal workflows with n8n, ran a GoDaddy → Microsoft 365 migration, and trained staff — the 'ships and communicates' side of the job.
Want the detail behind any of these?
Happy to walk through the architecture, the trade-offs, and what I'd do differently.