On AI Lounge since Nov 2026
Jordan Dominick
Member #6,013DeveloperL2Ai & ML Reseacher, Ignition Labs
Local inference optimization
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×4Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 4 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×4Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Jordan Dominick hasn't posted yet.
Pinned projects
Caminus: AI inference on AMD Radeon GPUs (RDNA3, ROCm/HIP), one kernel launch per token.
amdggufhipllm-inferencemoe
Your Windows desktop as redacted text for AI agents: an MCP server reading Win32 and UI Automation first, NPU vision for the pixels, secrets withheld on your PC.
accessibilityai-agentsamdcomputer-use
mcp
Lightweight, bare-metal inference engine and async vision runtime for AMD Ryzen AI (XDNA1) silicon.
Production-oriented Discord music bot: Lavalink v4 audio, SQLite persistence, AGPL-3.0-or-later
A top inspired dashboard for llama.cpp's llama-server or LM Studio, and the Qwen Code agents using it
ai-agentsbubbleteadashboardgolanggpu-monitoring
Where a Qwen3-30B-A3B decode token's matvec time goes on an RX 7900 XTX: launches, HIP graphs and persistent kernels (for iree#24165)
amdgpu-benchmarkhipllm-inferencerdna3
About
Jordan Dominick is an AI and ML researcher at Ignition Labs, where their work centers on local inference optimization. Open-source work by Jordan includes caminus, a project for running AI models on AMD Radeon GPUs, and Ignition, an engine aimed at AMD Ryzen AI processors. Recent public code includes ignite-scribe, which lets AI agents read a Windows desktop as redacted text.