Join NVIDIA as a Senior Software Engineer leading AI inference advancements. Work on large-scale LLM serving and drive performance improvements through hands-on customer collaboration.

This role at NVIDIA focuses on pushing the boundaries of AI inference technology within a customer-centric framework. You will engage with engineering teams to understand LLM architectures and performance goals, implement benchmarking across Kubernetes and Slurm, and develop profiling plans that yield actionable insights. Your contributions will enhance community tools like vLLM, driving efficiency and clarity in technical documentation.

Key Responsibilities:
• Interface with customer engineering teams on performance goals
• Design and execute benchmarking campaigns effectively
• Tweak vLLM serving deployments for performance metrics
• Automate and build benchmarking tools for efficiency
• Clearly document technical findings and insights

...