Join NVIDIA as an Expert Software Engineer focused on AI performance and optimization. This hybrid role emphasizes the development of high-performance inference for large-scale models. We need highly skilled engineers to collaborate on optimizing GPU kernels and architecting current inference frameworks.

The ideal candidate will bring over 5 years of industry experience, a solid understanding of ML systems, and proficiency in programming languages such as Python and C/C++. Your research contributions will help advance AI performance. Key Responsibilities:
Architect and optimize inference infrastructure and benchmarks
Contribute features to cutting-edge AI frameworks like vLLM
Conduct original research and integrate findings into production




Optimize GPU kernels with advanced techniques
Collaborate with multi-functional teams to enhance efficiency

Requirements:
Advanced degree (PhD, Master’s, or Bachelor’s) in relevant fields
5+ years of experience in software engineering
Robust programming skills in Python and C/C++, Go, or Rust
Knowledge of ML framework performance engineering
Effective debugging and problem-solving capabilities

Bring your deep expertise in software engineering and AI performance to NVIDIA's creative team.

📌 Expert Software Engineer In Ai Performance Toronto (Canada)
🏢 NVIDIA
📍 Canada