The Role
We're looking for someone who lives on the frontier of generative AI to join us in building the core of ComfyUI. You'll be the person who takes the newest open-source models (image, video, 3D, audio, multimodal…) and brings them into ComfyUI as first-class citizens, often within days of their release.
You are a good fit if this describes you:
You read new model papers as they drop and have opinions about them
You love diving deep into how models actually work under the hood
You've ported models from research into production and gotten the outputs to match
You know ComfyUI well, its architecture, workflows and have opinions about nodes design
You think the gap between research and production should be as short as possible
What you'll do:
Implement state-of-the-art open-source models to run natively in the ComfyUI core engine
Design and build the native nodes that expose new model capabilities cleanly to users
Work directly with our core team on architecting new features
Partner with the custom node community and help core absorb capabilities as they mature
Help shape where we take this technology next
Bonus: If you've worked with diffusion/LLM models before or built custom nodes for ComfyUI, that's awesome
Building ComfyUI
