Jamie Li

Jamie Li is a senior technical marketing engineer at NVIDIA focused on wrangling the latest technologies in AI inference. He brings a deep background in both AI software engineering and customer management, translating innovations into practical customer outcomes. Before NVIDIA, he held roles developing, breaking, and fixing AI solutions in the enterprise tech sector. He also did research in medical imaging and holds a master’s degree in Computer Science with an AI focus.
Avatar photo

Posts by Jamie Li

Data Center / Cloud Aug 24, 2026

NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt 

AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing... 9 MIN READ
Decorative image.
Trustworthy AI / Cybersecurity Jul 02, 2026

Hardware-Rooted AI Security That Won't Slow You Down

AI has transformed how organizations operate, driving unprecedented levels of productivity and innovation. However, AI adoption can be impeded by concerns... 6 MIN READ
Data Center / Cloud Feb 25, 2026

Making Softmax More Efficient with NVIDIA Blackwell Ultra

LLM context lengths are exploding, and architectures are moving toward complex attention schemes like Multi-Head Latent Attention (MLA) and Grouped Query... 10 MIN READ
Agentic AI / Generative AI Oct 13, 2025

NVIDIA Blackwell Leads on SemiAnalysis InferenceMAX v1 Benchmarks

SemiAnalysis recently launched InferenceMAX v1, a new open source initiative that provides a comprehensive methodology to evaluate inference hardware... 11 MIN READ
Developer Tools & Techniques Oct 07, 2025

Pruning and Distilling LLMs Using NVIDIA TensorRT Model Optimizer

Large language models (LLMs) have set a high bar in natural language processing (NLP) tasks such as coding, reasoning, and math. However, their deployment... 11 MIN READ
Data Center / Cloud Sep 17, 2025

An Introduction to Speculative Decoding for Reducing Latency in AI Inference

Generating text with large language models (LLMs) often involves running into a fundamental bottleneck. GPUs offer massive compute, yet much of that power sits... 11 MIN READ