Projects & experiments
Things I’ve built.
Video agents, visual search, and the infrastructure behind production ML. Each project brings together the story, code, demos, and research.
Projects
Cloudglue and Tinycloud
Cloudglue APIs and Tinycloud agents for turning video collections into searchable, queryable knowledge with replayable evidence.
Co-founder and CTO
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 engineerSee the work in motion
Product walkthroughs and technical presentations.
Tinycloud AI Video Agent Launch / Demos
A video agent that turns recordings into reports, apps, playlists, and searchable knowledge.
Watch on YouTubeAutonomous Video Hunter AI Agents for Real-Time OSINT
Agentic video analysis for target discovery, OSINT extraction, and grounded reports.
Watch on YouTubeCloudglue - Turn Videos Into Structured, LLM-Ready Data
Cloudglue as video context infrastructure for AI products.
Watch on YouTubeCloudglue MCP x Claude Desktop
Chat with videos inside an agent client through Cloudglue MCP.
Watch on YouTubeMLOps at Snapchat
Continuous machine learning with Kubeflow and Spinnaker at Snap.
Watch on YouTubeBuild Accurate Training Datasets with SageMaker Ground Truth
Training-data workflows, labeling quality, and model iteration.
Watch on YouTubeOut in the world
Shipped camera and AR experiences, from everyday scanning to live events.