Drive innovation at NVIDIA as a Senior Software Engineer in AI inference. Collaborate directly with customers to optimize LLM serving and performance scalability.
This impactful role involves partnering closely with engineering teams at NVIDIA to refine large-scale LLM serving solutions. Engage in both profiling and optimization of GPU deployments, focusing on performance improvements through benchmarking campaigns in cloud environments. Your work will not only enhance customer solutions but also contribute massively to open-source projects like vLLM, ensuring shared knowledge enhances engineering practices.
Key Responsibilities:
• Collaborate with customers to analyze LLM serving architectures
• Implement detailed benchmarking campaigns in Kubernetes
• Optimize GPU cluster deployments for performance gaps
• Develop end-user tools for improved team efficiency
• Document findings and enhance community contributions
Requirements:
• Advanced degree in Computer S...