AI demos are magic, but going from that to a reliable system your customers depend on is a whole other skill. I can do both. Think real-time agents assisting in global calls, or personal assistants that remember what you said three weeks ago.
Low-latency, voice-to-voice translation with voice cloning over WebRTC. Built to push the limits of streaming pipelines under real constraints.
Frictionless cross-language voice chat that feels instant while preserving speaker identity — over real networks, not lab conditions.
The project is not yet ready to demo. But here is a look at what is possible. The following was made by cloning my voice speaking English
Still working on this in my free time. Building this as a solo dev is quite the challenge as there are a lot of areas that need refinement to turn a proof of concept into something that is production ready.
A powerful desktop voice assistant with persistent memory, self-tool generation, and deep OS integration. Built to outperform mainstream assistants on contextuality and actionable help.
Speech is about ~3-5 times faster than typing. Being able to trigger voice typing with a wake word and switch to an intelligent assistant is something I've wanted ever since seeing the movie Her. I'm not quite there yet but it is shockingly close.
This was my first ever YouTube video, I'll improve and gain confidence talking to myself on camera, but for now please bear with it. :) I noticed people stopped watching before even seeing the interesting part, so I've now set this to skip right to it. Feel free to go back if have a higher tolerance for rambling.
Beats Siri/Google/Alexa on context handling, adaptability, and actual task execution — while running locally for privacy and low latency.
Solo • August 2024 - Now
I decided it was time to work on my own dreams and study things I really wanted to learn.
I ended up pivoting away from the feedback site after a recent technical breakthrough made my current project feasible (see above). However I intend to come back and finish the feedback application as it is something that needs to exist. I feel much of the world's current issues, both large and small stem from people not feeling free to speak honestly with each other.
Workday • August 2021 - 2024
Supported global applications in data centers, GCP, and AWS Kubernetes clusters. Focused on automating operations to simplify management of customer-impacting issues and enhance recovery times.
Key achievements:
Container Solutions • August 2019 - August 2020
Client-facing consulting work improving how organizations build and deliver software using cloud-native technologies.
Key achievements:
Marketplacer • November 2016 - June 2019
Development, platform scalability and data integrations for two of the biggest clients on the platform.
Key achievements:
Vinomofo • August 2016 - November 2016
Key achievements:
Netfira Pty. Ltd. • 2012 - 2015
Multiple roles with increasing responsibility: Senior Developer → Lead Web Dev/Ops → Senior Dev/Ops (External)
2006 - 2012
I started out as a developer, but quickly discovered I was just as fascinated by the infrastructure that keeps software running. SRE was the perfect fit — using programming to automate away infrastructure headaches.
Plot twist: After 15+ years of making systems more reliable, faster deployments, and bulletproof monitoring, I got completely hooked on AI. Not the hype part — the engineering challenge of making these systems actually work when real people depend on them.
What I'm building right now: A real-time translation system that works over terrible WiFi (seriously, try video calling from a coffee shop), and a personal assistant that remembers context across conversations. Both sound simple until you try to make them reliable enough for daily use.
My weird advantage: I bring the same "this needs to work at 3am when everything is broken" mindset to AI systems. If your AI demo is impressive but falls over under load, or costs $50 per conversation, let's talk.