Join NVIDIA as a Senior Software Engineer dedicated to AI inference systems. Focus on developing and optimizing high-performance computing in a hybrid work setup. In this pivotal role, you will be at the forefront of building advanced AI systems and optimizing GPU functionalities. Your expertise is essential for enhancing frameworks like vLLM, promoting efficiency across multiple platforms while collaborating with various teams to push the boundaries of ML systems. Key Responsibilities:
Contribute optimizations to GPU kernels and compilers
Architect productive AI inference stacks for scalable deployments
Develop benchmarking tools for industry-leading standards
Lead orchestration of multi-cloud AI deployments
Research innovations to enhance ML Systems technologies Requirements:
7+ years in software engineering or relevant higher education
Solid programming foundation in Python and C/C++
Familiarity with performance engineering in ML frameworks
Experience with containerization tools like Docker
Excellent problem-solving and communication skills Make a significant impact on AI technologies and contribute to pioneering projects at NVIDIA.

📌 Nvidia Senior Software Engineer, Ai Inference Toronto
🏢 NVIDIA Gruppe
📍 Toronto