Join NVIDIA as a Senior Software Engineer to enhance AI inference systems. Focus on optimizing GPU performance and scaling workloads across complex environments in this exciting role.
In this position, you will collaborate with teams on cutting-edge AI systems and artifacts. Your primary responsibility will be optimizing the vLLM inference framework and contributing to advanced GPU kernels. With a focus on multi-GPU and multi-cloud deployments, you will also participate in benchmarking methodologies that set industry standards.
Key Responsibilities:
• Architect and implement high-performance inference stacks
• Optimize GPU kernels using fusion and autotuning techniques
• Contribute to MLPerf Inference benchmarking suite
• Collaborate on container orchestration for AI workloads
• Engage in research to advance performance in ML systems
Requirements:
• Master’s in relevant field with 5+ years of experience
• Proficient in Python and C/C++ programming language...