Elevate your career in AI inference with NVIDIA as a Senior Software Engineer. Collaborate on large-scale LLM serving while enhancing GPU deployment performance and efficiency.
NVIDIA seeks a Senior Software Engineer focused on AI inference to engage directly with customer engineering teams. Combining hands-on technical consultation with deep systems expertise enables you to design and implement benchmarking campaigns in Kubernetes and Slurm environments. You will profile real deployments, develop performance plans, and build tools that enhance team productivity while contributing back to open-source communities.
Key Responsibilities:
• Partner with customers to understand LLM architectures
• Design end-to-end benchmarking campaigns for insights
• Optimize vLLM serving deployments on GPU clusters
• Develop internal tools and automation pipelines
• Document findings and share improvements with the community
Requirements:
• Bachelor's, Master's, or PhD in relev...