Principal Software Engineer - AI Inference

NVIDIA seeks a Principal Software Engineer - AI Inference to advance open-source LLM serving. The role involves contributing to upstream inference engines like vLLM and SGLang, ensuring they run outstandingly on NVIDIA GPUs and systems.

Requirements

• 15+ years building production software with significant depth in systems engineering
• Demonstrated expertise in LLM inference/serving systems (e.g., vLLM, SGLang)
• Strong programming skills in Rust, C++, Python, CUDA
• Experience with GPU performance analysis tools and methodologies
• Solid foundation in distributed systems and concurrency

Benefits

• Equity
• Benefits