On AI Lounge since Nov 2026
Alex Weng
Member #4,316DeveloperL2ai engineer, independent
AI Research, Inference & Agentic Engineering
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 ×3Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 3 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×3Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Alex Weng hasn't posted yet.
Pinned projects
Profile README
Your personal AI guardian of knowledge - macOS app for document research with MLX
NVIDIA Nemotron-3-Diarization speaker diarization for vLLM (out-of-tree plugin)
NVIDIA Parakeet TDT (parakeet-tdt-0.6b-v3) transcription plugin for vLLM
About
Alex Weng is an independent AI engineer based in Toronto, Canada, focused on AI research, inference and agentic engineering. Alex builds open-source tools for vLLM, including a speaker diarization plugin for NVIDIA Nemotron models and a Parakeet transcription plugin, and has also released a macOS app for document research built with MLX. Recent public work centers on model inference and agentic engineering, with several repositories updated in the past month.
