We're looking for someone who loves optimizing model inference to join us in building the core of ComfyUI - the most complex and bleeding-edge part of our engine. You'll be working on making AI models run faster and more efficiently than anyone thought possible.
You are a good fit if this describes you:
You geek out about model inference, torch optimizations, and memory management
You've written production PyTorch code that pushes performance boundaries
You love diving deep into how models actually work under the hood
You get excited about making insanely optimized code that just works
You think the current state of ML deployment could be way better
What you'll do:
Build and optimize the core inference engine that powers ComfyUI
Make massive models run faster and use less memory than anyone else
Work directly with our core team on architecting new features
Tackle the hardest technical problems in the visual AI space
Help shape where we take this technology next
If you've worked with diffusion/LLM models before or built custom nodes for ComfyUI, that's awesome
What is ComfyUI?ComfyUI is the world’s leading visual AI platform — an open, modular system where anyone can build, customize, and automate AI workflows with precision and full control.
Unlike most AI tools that hide their inner workings behind a simple prompt box, ComfyUI gives professionals the freedom to design their own pipelines — connecting models, tools, and logic visually like building blocks.
It’s used by artists, filmmakers, video game creators, designers, researchers, VFX houses, and among others, teams at OpenAI, Netflix, Amazon Studios, Ubisoft, EA, and Tencent — all who want to go beyond presets and truly shape how AI creates.
ComfyUI empowers those who were not trained with the power of the brush to also be a painter, and those who are, to be a maestro.
Built for users who value transparency and control Infinitely extensible — thousands of community-made nodes and integrations
Scales from creative experimentation to production automation
Open-source, used by millions, and backed by one of the most active AI communities online
Evolving to democratize visual AI creation: empowering everyone from hobbyists to studios, storytellers, and enterprises to be more productive and creative than ever before
ComfyUI isn’t just another AI app. It’s aiming to become the operating system for visual generative AI , the foundation on which the next generation of creative tools are being built.
An creative’s show case of how Comfy is adopted in their work
We are a small, intense, and well-funded team in San Francisco who push ComfyUI and its ecosystem forward. Our team comes from Stability AI and Google and many contributed to the ComfyUI ecosystem way before working here.
Our organization is flat and there is no hierarchy, only categories: dev, arts, prod, ops, etc (and no, there is no one here with the title of Member of Technical Staff, it’s long and silly for a job title).
The only thing that matters is the quality of your cultural fit and execution. We work hard and demand a lot of each other. But we have fun: everyone is here to make something meaningful that will end up being our life’s work. If this mission excites you and you view yourself as a top-tier talent, your future latent self is waiting for you at Comfy.
Check out our Github and blog for what we’ve been working on. Our investors include Pace Capital, Chemistry, Abstract Venture, and Guillermo Rauch.
Top Skills
What We Do
Building ComfyUI
