Job Description
NVIDIA is looking for a Senior Software Engineer focused on building high-performance AI inference systems. Leverage your expertise in GPU optimization and distributed systems in a dynamic, innovative environment.
This senior role requires software engineers with expertise in AI inference and systems design. You will contribute to the vLLM framework, optimize GPU kernels, and architect large-scale deployments across multi-cloud environments. Your work will drive industry benchmarks and involve collaboration with diverse teams in the realm of accelerated computing.
Key Responsibilities:
• Develop features for vLLM leveraging NVIDIA GPU hardware
• Optimize and benchmark GPU kernels using advanced techniques
• Define methodologies for inference benchmarking tools
• Architect scheduling for large-scale containerized inference deployments
• Conduct original research to enhance ML Systems capabilities
Requirements:
• ...
This senior role requires software engineers with expertise in AI inference and systems design. You will contribute to the vLLM framework, optimize GPU kernels, and architect large-scale deployments across multi-cloud environments. Your work will drive industry benchmarks and involve collaboration with diverse teams in the realm of accelerated computing.
Key Responsibilities:
• Develop features for vLLM leveraging NVIDIA GPU hardware
• Optimize and benchmark GPU kernels using advanced techniques
• Define methodologies for inference benchmarking tools
• Architect scheduling for large-scale containerized inference deployments
• Conduct original research to enhance ML Systems capabilities
Requirements:
• ...