Senior Engineer for GPU Inference at NVIDIA (Toronto)

Job Overview

Join NVIDIA as a Senior Engineer and build cutting-edge AI inference systems that serve large-scale models with astounding efficiency. Focus on optimizing GPU performance and collaborating with top experts.

In this pivotal role, you will have the opportunity to architect high-performance inference stacks and optimize NVIDIA's GPU solutions for maximum productivity. Your expertise will be instrumental in achieving industry-leading benchmarks and implementing state-of-the-art GPU kernels within a collaborative, multi-cloud framework.

Leverage your skills in performance engineering at NVIDIA to drive AI innovation.

Key Responsibilities

• Develop and optimize features for vLLM with latest GPU tech


• Benchmark and profile GPU kernels for efficiency


• Create tools for inference benchmarking methodologies


• Lead orchestration of large-scale inference deployme...