Reuben Stanley, researcher in machine learning for dynamical systems, optimisation and control at UWA.

Machine Learning · Dynamical Systems · Control

Reuben

Driven by an insatiable need to understand; to ask 'why'.

Who I am

I build control systems that learn.

I'm an Honours student researching machine learning for dynamical systems, optimisation and control at the University of Western Australia (UWA). The systems I care about are highly nonlinear and notoriously hard to model and control. The question under the work: how can a system make sense of a complex, constantly adapting world, and know what to do in it?

Where I'm going

What keeps pulling me forward.

The future is drawing me on: a fascination with consciousness, the mind, and the nature of intelligence; with dynamical systems, their modelling and control; with the renewable energy that will power what comes next.

scroll

The centrepiece

Machine Learning Engineer · WaveX

Machine learning for wave energy.

At WaveX, an Australian wave-energy company, I'm developing an intelligent, learning control system to maximise power generation in the highly nonlinear environment of ocean waves, across a converter of multiple independent bodies that move and couple together. I'm also building the 3D simulation environment used to visualise the system and the data flowing through it. WaveX is sponsoring my honours project.

Learning-based control Multi-body WEC Nonlinear dynamics 3D simulation

Selected work

Things I've built.

Startup · Computer vision

CosineOne

Real-time AI security alerts for high-stakes sites. A full-stack build (FastAPI backend, JS frontend) with alerts surfaced both as a live overlay and through a Telegram bot. At its core is a private, on-device ML pipeline that validates custom natural-language alerts like "person taking something from the backyard." I built the pitch deck and demo, and engaged mining and defence prospects for pilots.

On-device MLLive + Telegram alerts
Startup · AI automation

TradieBuddy

An AI automation CRM that books jobs for tradies without a human in the loop. A scheduling algorithm uses the Google Maps API to slot new jobs into the calendar optimally, minimising travel between sites, and offers new leads the best available appointment instantly instead of waiting for an admin to call back. Faster bookings, fuller days, less drive time.

Route-optimised schedulingInstant lead booking
Contract · ML engineering

Semantic camera-roll search

Re-architected the backend for a semantic photo-search app, cutting average search latency from 180s to under 7s (about a 96% drop) while pushing retrieval accuracy to near-perfect. Built the text and image embedding pipelines, face and object tagging, and optimised inference to hit the production SLO. Also authored a reusable Python library for spinning up AI agents and wiring LLM tools into conversational photo search.

180s → <7s (≈96%)~100% retrieval
Check out my GitHub →

Background

I started a consultancy.

In 2024 I founded an AI and software consultancy through VentureUWA's startup incubator, delivering data, machine-learning and automation work for companies across engineering, healthcare and global manufacturing, and growing it past six figures in revenue.

6-figure revenue VentureUWA incubator · 2024 Engineering to MNCs
Selected clients
Work Air Tech · engineering Apollo Healthcare Technologies · healthcare Freudenberg · global manufacturing
FounderAI & software consultancy
via VentureUWA incubator · 2024
Technical Vice-PresidentQFin (Quantitative Finance Club)
University of Western Australia
Technical LeadVentureUWA
Student venture program

Hackathons

Friday brief, Sunday demo.

A weekend, a problem I've never seen before, and a team figuring it out together in real time. That's my idea of a good time. I keep doing them for the pace, the people, and how much you learn when you have to ship something real by Sunday.

1st BHP Hackathon
1st Spacecubed Startup Weekend
1st Genvis × VentureUWA Hackathon
Initialising