Four projects, one from each discipline I work across: 3D and spatial, product, marketing, and AI.
A navigable solar system where every world is a real 3D Gaussian splat trained from open planetary data, not a texture painted onto a sphere.
A multi-tradition natal-reading practice synthesising Western, Chinese BaZi and Vedic Jyotish, with predictions logged so they can be checked.
Brand and landing-page proposal work for an AI-native home OS, plus a real sales-journey script for its physical showroom demo unit in Dubai.
BARNES Dubai's internal data tooling: an entity-centric valuation platform and AVM, absorbed into a broker tool over ~840,000 ownership records.
On-stand at four international tech expos.
Living Homes: GITEX Global 2024 (Dubai) · LEAP 2025 (Riyadh) · GITEX Asia 2025 (Singapore). Both brands: GITEX Global 2025 (Dubai)
Research
3D Gaussian Splatting
Method-paper quality, running on a mobile budget.
Radiance fields on a phone budget
The Kerbl et al. 2023 paper swapped NeRF’s neural network for millions of explicit 3D Gaussians, and the field exploded into dozens of implementations, each trading off training speed, render quality, and runtime fidelity differently. The benchmark closes the gap between method papers and what actually deploys to a Safari-iOS budget. Barnes Vantage is the shipped answer, running in production on the BARNES Dubai property-search flow.
About
Creative direction, backed by a design background: I take an idea and give it working form, using whatever tool actually gets it there, and I ground the work in research and testing rather than in demos alone. In practice, that has meant a real-time Gaussian-splat research pipeline, generative-video launch films, brand visibility inside AI answer engines, and representing brands on-stand at global tech expos. The throughline is taking an emerging technique from first experiment to something a business can put in front of a client.
The way I work: start from what the people around a project need, find out whether the technology can carry it, and only then put a proposal in front of anyone. I build far enough to prove the idea works, then hand it on. Colleagues get trained on the capture work and the AI tooling, and the workflows end up used by teams outside the one that asked for them.
A little personality, not just the résumé version
Contact
Open to a conversation about applied AI, 3D, or the next problem worth solving. Remote-first, reachable anywhere.
If it is a project you want built, here is what that looks like.
