Senior/Staff ML Engineer, Performance Optimization

comfy-org; San Francisco (CA); On-site; USD 100,000 - 140,000; Full time

Job summary

comfy-org is seeking an AI Optimization Engineer in San Francisco to enhance model inference performance for ComfyUI. The role entails building and optimizing the core inference engine, ensuring models run faster and use less memory.

Ideal candidates are passionate about model optimization, have production experience in PyTorch, and enjoy tackling technical challenges in the visual AI domain. This position offers a unique opportunity to influence cutting-edge technology.

Qualifications

• Experience optimizing model inference and memory management.
• Proficiency in production PyTorch code.
• Passion for exploring how models function internally.

Responsibilities

• Build and optimize the core inference engine for ComfyUI.
• Enhance model performance and reduce memory usage.
• Collaborate with the core team on feature development.
• Address technical challenges in visual AI.
• Influence the direction of the technology.

Skills

Model inference optimization

Torch optimizations

Memory management

Production PyTorch code

Visual AI problems

Job description

The Role

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

Bonus

If you’ve worked with diffusion/LLM models before or built custom nodes for ComfyUI, that’s awesome.