Take your career to the next level as a Senior Performance Software Engineer specializing in AI inference systems. Enhance large-scale model efficiency through collaborative innovation. In this pivotal role, you will contribute to building exceptional AI inference systems and optimize GPU performance for cutting-edge models.

You'll collaborate with cross-functional teams and help advance performance benchmarks while architecting novel solutions in machine learning infrastructure. Your original research will play a vital role in pushing the boundaries of AI. Key Responsibilities:

- Empower vLLM with the latest AI model features
- Optimize the inference framework using advanced techniques
- Create runtime optimizations and architect frameworks
- Conduct research, integrating ideas into production-ready software
- Develop and benchmark hand-tuned GPU kernels Requirements:
- Bachelor's, Master's, or PhD in relevant fields
- 5+ years of applicable industry or research experience
- Proficient in Python and C/C++, Go, or Rust
- Solid foundation in parallel programming and distributed systems
- Familiar with profiling tools and GPU programming techniques Shape the future of AI through efficiency and performance!

📌 Senior Performance Software Engineer (Toronto)
🏢 United States Digital Space
📍 Toronto