LinkedIn Just Quietly Solved Open-Source ML Infra’s Real Bottleneck — And Almost Nobody Noticed

Agents are now writing the GPU kernels that train the agents. The design pattern underneath it is what you should actually steal. The most interesting ML infra release of April 2026 wasn’t a model. It was a blog post from LinkedIn’s Liger Kernel team - buried under the standard “AI helping build better AI” framing that nobody clicks on anymore - describing three agentic workflows that now write Triton GPU kernels, integrate new model architectures, and optimize existing kernels with minimal human input.