Elevate AI inference capabilities at NVIDIA as a Senior Software Engineer! This role merges your systems knowledge with direct customer engagement, focusing on optimizing performance in LLM serving.
As a Senior Engineer at NVIDIA, you will engage with top-tier clients to understand their architecture and performance goals. This entails setting up benchmarking campaigns, operating vLLM on GPU clusters, and documenting actionable insights. Your work will drive improvements not only for customers but also for the broader open-source community.
Key Responsibilities:
• Work closely with customer engineering teams on performance goals
• Design and conduct benchmarking campaigns on GPU clusters
• Optimize configurations for efficient vLLM deployments
• Create tools and automation pipelines for team enhancement
• Draft clear documentation of findings for technical audiences
Requirements:
• Advanced degree in Computer Science or related field
• Minimum 5 years in c...