Cloudglue and Tinycloud
Cloudglue APIs and Tinycloud agents for turning video collections into searchable, queryable knowledge with replayable evidence.
Co-founder and CTO
Hi, I’m Kevin Dela Rosa.
I take AI to production.
From research to real users.
I’ve shipped AI at every scale, in consumer products and the infrastructure behind them: product matching across Amazon’s catalog, visual search and OCR for hundreds of millions of Snapchatters along with the ML platform that trained them, and now video agents at Cloudglue, where I’m co-founder and CTO.
Open to speaking and consulting. Message me on LinkedIn.
- publications
- 22
- patents
- 11
- users reached
- 100M+
Shipped and spoken at Super Bowl LV · Cannes Lions · Art Basel · DEF CON · KubeCon · AWS re:Invent
Published at NeurIPS · ICCV · CVPR · WACV · KDD · ACM WWW · SIGIR · ACM RecSys · ACM CAIS · NAACL · ISMIR
Work
Products, open-source tools, and systems shipped at scale.
Overcast
A video OSINT agent that searches, listens, matches, maps, and remembers across a collection of video.
Creator
mDex
An offline card scanner and open-source visual matcher. A computer-vision rabbit hole, built for a real card show.
Creator
Autonomous Video Hunter
A video-agent system for real-time OSINT: find targets, extract signals, and generate grounded reports.
DEF CON 33 Recon Village speaker
Snapchat Scan and Visual Search
Computer vision and retrieval systems shipped into Snapchat camera, Scan, search, messaging, and AR.
Staff ML Engineer and Tech Lead Manager
ML Infrastructure at Snap
Continuous ML, labeling, training, deployment, and GPU infrastructure for camera intelligence and gen AI.
Tech lead and manager
Applied AI, Search, and Language Tech
Information retrieval, NLP, learning systems, product matching, and practical AI.
Researcher and software engineerTalks & demos
Conference talks and live demos on video agents, retrieval, and production ML.
2026
2026
2025
2025
2025
2020
2019
2015
Product demos: Tinycloud launch demo · Cloudglue MCP with Claude Desktop
Research
Selected papers on multimodal retrieval, video agents, and computer vision.
2026
2025
2025
2025
2025
2023
2021
Also an inventor on 11 patents in visual search, scanning, OCR, and ML systems.
Writing
The ideas, experiments, and decisions behind the work.
I put every CSI button in a CLI
Building Overcast: the real algorithms behind the hacker-movie tropes, connected to an agent that remembers.
mDex is open source: bring your own catalog
Bring your own catalog to the offline visual matcher, and reproduce the benchmarks behind it.
I vibe coded an offline card scanner for the National
10,023 trading cards, an offline iPhone scanner, and a return to classic computer vision.
About
Speaking & consulting
I give talks and live demos on video agents, retrieval, and production ML, and consult on taking AI systems to production. Message me on LinkedIn with the event or project, timing, and format.