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
About ComfyComfy (https://www.comfy.org) is the AI creation engine for visual professionals who demand control over every model, every parameter, and every output. The most powerful workflow engine for visual AI.
Unlike tools that hide everything behind a prompt box, Comfy lets you connect models, processing steps, and outputs on a canvas where every decision is visible and every step is inspectable. It gives you the building blocks to create workflows nobody's imagined yet, and share them with everyone.
What started as an open-source project in 2023 now has 4 million users, 60,000+ community-built nodes, and 150,000+ daily downloads. It's used by artists, filmmakers, game studios, designers, researchers, and VFX houses, including teams at OpenAI, Netflix, Amazon Studios, Ubisoft, EA, and Tencent.
We're a small, intense team in San Francisco. Our team comes from Stability AI and Google, and many contributed to the ComfyUI ecosystem long before working here. Low ego, high ownership. We work hard and demand a lot of each other, but we have fun. Everyone here is building something meaningful that will end up being our life's work.
If this mission excites you and you view yourself as top-tier talent, your future latent self is waiting for you at Comfy.
Check out our Github (https://github.com/comfyanonymous/ComfyUI) and blog (https://blog.comfy.org). We recently raised $30M at a $500M valuation. The round was led by Craft, with participation from Pace Capital, Chemistry, TruArrow, and others.
Skills Required
- Experience with production-grade PyTorch code
- Deep understanding of model inference, optimizations, and memory management
- Experience with diffusion/LLM models
What We Do
Building ComfyUI
.png){kind=logo}
