Join our creative team as an AI Performance Software Engineer, building advanced inference systems for large-scale models with cutting-edge GPU optimization. Collaborate with experts and drive efficiency in accelerated computing. We are seeking top-tier software engineers to architect and implement high-performance AI inference software.

In this role, you’ll focus on optimizing GPU kernels and driving benchmarks while collaborating with various teams. Your contributions will significantly enhance the efficiency of machine learning frameworks and inference engines like vLLM and SGLang. Key Responsibilities:
Develop features for vLLM utilizing the latest GPU hardware
Profile and optimize inference frameworks and algorithms




Architect novel frameworks and runtime optimizations
Conduct and publish original research in ML Systems
Develop and benchmark GPU kernels using performance techniques Requirements:
Bachelor's, Master's, or PhD in Computer Science or related field
5+ years industry experience in software engineering or research
Solid programming in Python and C/C++, Go, or Rust
Passion for performance engineering in ML frameworks
Excellent debugging and communication skills Elevate AI systems and contribute to groundbreaking research with us today.

📌 Ai Performance Software Engineer Role Toronto (Canada)
🏢 United States Digital Space
📍 Canada