Drive innovation at NVIDIA as a Senior Engineer specializing in high-efficiency AI inference systems. Utilize cutting-edge GPU technology to optimize large-scale AI models effectively.

In this senior position, you will leverage extensive software engineering expertise to advance AI frameworks. You'll contribute to improving inference stacks, support groundbreaking research, and empower developers to utilize GPU features fully. This role demands a strong commitment to excellence in AI model performance and innovation.

Key Responsibilities:
• Develop advanced AI model features using vLLM
• Optimize GPU kernels and compilers for enhanced performance
• Create strategies for inference benchmarking
• Oversee the deployment orchestration of inference
• Research and integrate innovative machine learning concepts

Requirements:
• PhD or 7+ years in AI or a related field
• Proficient in Python, C/C++, and performance...