Senior/Staff ML Engineer, Performance Optimization

Responsibilities

• Build and optimize the core inference engine that powers ComfyUI
• Make massive models run faster and use less memory
• Work directly with the core team on architecting new features
• Tackle complex technical problems in the visual AI space
• Help shape the future direction of the technology

Requirements

• Deep interest in model inference, torch optimizations, and memory management
• Experience writing production PyTorch code focused on performance boundaries
• Strong understanding of model internals and low-level mechanics
• Ability to write highly optimized code

Preferred Qualifications

• Experience working with diffusion or LLM models
• Experience building custom nodes for ComfyUI