17 Aug
|
NVIDIA AI
|
Ontario
NVIDIA seeks highly skilled software engineers to build AI inference systems for large-scale models in Toronto, Canada. You will design high-performance inference software, optimize GPU kernels, and drive benchmarks across inference performance, kernels, training, serving, and research teams.
Responsibilities include contributing features to vLLM, profiling and optimizing the framework, and publishing research that advances ML systems.
#J-18808-Ljbffr
📌 Senior AI Inference Performance Engineer (Equity) (Ontario)
🏢 NVIDIA AI
📍 Ontario