NVIDIA Senior Engineer in AI Inference

Lead the charge in AI innovation as a Senior Engineer at NVIDIA, specializing in high-efficiency AI inference systems. Your work will optimize performance on large-scale AI models, utilizing cutting-edge GPU capabilities.

This position requires deep technical expertise in software engineering and a strong background in AI frameworks. You'll play a crucial role in optimizing inference stacks, contributing to groundbreaking research, and developing tools that empower developers to utilize GPU features effectively.

Key Responsibilities:
• Develop features for advanced AI models using vLLM
• Optimize and benchmark GPU kernels and compilers
• Create and define inference benchmarking strategies
• Oversee the orchestration of inference deployments
• Research and integrate novel ideas from ML publications

Requirements:
• PhD in related field or 7+ years experience in industry
• Proficient in Python and C/C++, with...