Harry Kim

Harry Kim is a Principal Product Manager at NVIDIA enabling performant and scalable AI/ML inference with Triton. He has experience working on recommendation systems at Meta, AI infrastructure at Intel AI, and Ads ranking and recommendation at Google. He holds a PhD in Statistics from UC Berkeley.
Avatar photo

Posts by Harry Kim

Agentic AI / Generative AI

Reducing Rollout Bottlenecks in Reinforcement Learning with NVIDIA Dynamo

Reinforcement learning (RL) uses rewards to train models to solve problems and complete tasks more successfully. Inference drives this process. Workers generate... 7 MIN READ
Agentic AI / Generative AI

NVIDIA Dynamo Accelerates llm-d Community Initiatives for Advancing Large-Scale Distributed Inference

The introduction of the llm-d community at Red Hat Summit 2025 marks a significant step forward in accelerating generative AI inference innovation for the open... 5 MIN READ
Data Center / Cloud

NVIDIA Dynamo Adds GPU Autoscaling, Kubernetes Automation, and Networking Optimizations

At NVIDIA GTC 2025, we announced NVIDIA Dynamo, a high-throughput, low-latency open-source inference serving framework for deploying generative AI and reasoning... 7 MIN READ
Developer Tools & Techniques

NVIDIA Dynamo, A Low-Latency Distributed Inference Framework for Scaling Reasoning AI Models

NVIDIA announced the release of NVIDIA Dynamo at GTC 2025. NVIDIA Dynamo is a high-throughput, low-latency open-source inference serving framework for deploying... 14 MIN READ
Agentic AI / Generative AI

Measuring Generative AI Model Performance Using NVIDIA GenAI-Perf and an OpenAI-Compatible API

NVIDIA offers tools like Perf Analyzer and Model Analyzer to assist machine learning engineers with measuring and balancing the trade-off between latency and... 6 MIN READ