NVIDIA Developer
NVIDIA DeveloperVideo
- Format:
- YouTube channel
- New videos:
- Several times a week
- Typical length:
- about 50 minutes, not counting Shorts
- Latest video:
About this show
If you’re building with NVIDIA technology, you’re in the right place.
Find practical tutorials, technical deep dives, demos and talks from NVIDIA engineers and the developer community. We cover CUDA, AI agents, generative AI, robotics, data science, computer vision, simulation, high performance computing and more.
Whether you’re just getting started or optimizing something already in production, subscribe for new videos to help you build.
Covers: AI development, nvidia technology, physical AI, robotics, generative AI, AI agents, computer vision, edge AI, large language models, machine learning tutorials
Videos come from the channel's public YouTube feed. The artwork is the newest video thumbnail. Last updated . Names, artwork and text belong to their publishers.
Recently on this show
Summary of recent videos, drawn from the publisher's feed.
NVIDIA Developer is a video channel for people building with NVIDIA technology, covering topics such as CUDA, AI agents, robotics, and computer vision. Recent videos include a Jetson livestream on building physical AI applications, a Mercedes-Benz factory talk on AI agents, and a Nemotron 3.5 Transcribe livestream.
Cosmos
Similar in subject
- AI Space
Both cover: robotics, large language models, ai agents - Practical AI
Both cover: physical ai, ai agents - ThursdAI - The top AI news from the past week
Both cover: generative ai, large language models
Similar shows
Videos
NVIDIA Dynamo in 5 Minutes: Dynamo On Kubernetes for AI Inference
· 5 min
Your model endpoint works for a demo. What does it take to scale it for your team? In this episode of Dynamo in 5 Minutes, we walk through deploying NVIDIA Dynamo on Kubernetes, from defining your serving setup to sending requests to a live endpoint. You’ll learn: • How the Dynamo Operator creates and manages your serving setup • Two deployment paths: describe what you need with DGDR, or customize an existing deployment recipe with DGD • How requests move from an OpenAI-compatible frontend to inference engines such as SGLang, vLLM, or TensorRT-LLM • The full DGDR workflow in a live demo, from deployment spec to a working endpoint No prior experience with distributed inference required.. ➡️ Learn more: https://www.nvidia.com/en-us/ai/dynamo/ 📝 Tech blog: https://developer.nvidia.com/blog/tag/nvidia-dynamo/ 📥 Download: https://github.com/ai-dynamo/dynamo Chapters: 00:00 Introduction 00:31 Moving beyond a single model server 01:02 How the Dynamo Operator works 01:38 Two deployment paths: DGDR and DGD 02:45 Request flow and architecture 03:59 Demo: From deployment spec to live endpoint 04:52 Wrap-up
Not rated yetBuild Visual AI Agents With NVIDIA Nemotron 3.5 Super VL
· 3 min
Learn how NVIDIA Nemotron 3.5 Super VL investigates why an AI bill rose 30% using a dashboard screenshot and a scanned pricing sheet. In this walkthrough, Chris Alexiuk introduces the open 120-billion-parameter mixture-of-experts model with 12 billion active parameters, then Chia-Chih Chen demonstrates a visual investigation agent. The agent reads the dashboard, identifies a surge in thinking-token use, writes Python to compare routing options and prepares a proposal for human approval. The recommended plan stays within the team’s quality bar while projecting about $100,000 in monthly savings. NVIDIA Nemotron 3.5 Super VL combines multimodal reasoning, tool use and code generation for agents that work across text, images, charts, documents and video. It can also run on a single NVIDIA DGX Spark. Use the links and chapters below to explore the model, technical blog and developer resources. ➡️ Learn more: https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/ 📝 Technical blog: https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/ 📥 Download the model: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 🚀 Try on NVIDIA Build: https://build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b 📚 Super VL cookbook: https://github.com/NVIDIA-NeMo/Nemotron/tree/main/usage-cookbook/Nemotron-3.5-Super-VL/visual-investigation-agent 📄 Technical report: https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf Chapters: 00:00 – Introduction 00:07 – NVIDIA Nemotron 3.5 Super VL overview 00:31 – Vision-language capabilities 01:09 – Multimodal billing investigation demo 01:46 – Read dashboard metrics 01:54 – Parse a scanned pricing sheet 02:01 – Find the cause of the cost increase 02:09 – Optimize ticket routing with Python 02:16 – Prepare a proposal for human review 02:28 – Cookbook and developer resources
Not rated yetIntroducing NVIDIA Nemotron 3.5 Super VL
· 1 min
Meet NVIDIA Nemotron 3.5 Super VL, an open, customizable multimodal model built for long-running agents. Watch it spot store hazards and analyze charts to explain rising AI costs. Super VL combines text and visual understanding with reasoning and tool use. Customize it with NVIDIA NeMo to improve accuracy and efficiency for specialized tasks. ➡️ Learn more: https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/ 📝 Technical blog: https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/ 📥 Download the model: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 🚀 Try on NVIDIA Build: https://build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b 📚 Super VL cookbook: https://github.com/NVIDIA-NeMo/Nemotron/tree/main/usage-cookbook/Nemotron-3.5-Super-VL/visual-investigation-agent 📄 Technical report: https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Super-and-Lightning-Technical-Report.pdf
Not rated yetSpark your Development | NVIDIA RTX Spark
· 1 min
Build local AI wherever you go with NVIDIA RTX Spark. Fine-tune and run large models, code with AI agents, and put AI assistants to work—all on your laptop, with the full CUDA stack on Windows on Arm. Build locally. Deploy anywhere. Learn more about NVIDIA RTX Spark: https://www.nvidia.com/en-us/products/rtx-spark/
Not rated yetYou give an AI agent a task. What happens next?
· 33 sec
This video walks through how agents use models and tools to complete tasks, and what makes them fast and responsive. No technical background needed.
Not rated yetHow AI Agents Work: Inside Agentic Inference
· 7 min
What happens when an AI agent starts working, and how do we measure its performance? In this episode of Inside the Architecture, we break down how AI agents use models, tools, and context to complete tasks. Follow the work through animated diagrams, then explore how benchmarks and inference infrastructure shape the experience. You’ll learn: How agentic workflows differ from a single prompt and response How tool calls, subagents, and growing context change the workload Why fixed-length tests and recorded-session replay measure different things How to interpret interactivity, latency, concurrency, and throughput Where NVLink, NVIDIA Dynamo, NVFP4, and TensorRT-LLM fit into the system No prior experience with inference infrastructure required. #AgenticAI #nvidia Benchmark results and methodology: https://developer.nvidia.com/blog/nvidia-vera-rubin-and-blackwell-set-a-new-standard-for-agentic-ai-performance-per-watt/ NVIDIA Dynamo architecture: https://developer.nvidia.com/blog/introducing-nvidia-dynamo-a-low-latency-distributed-inference-framework-for-scaling-reasoning-ai-models/ 00:00 From Chat to AI Agents 00:48 How AI Agents Work 02:28 How Agentic Benchmarks Work 03:37 Which Metrics Matter? 04:32 Where Do Performance Gains Come From? 05:22 Understanding Benchmark Results 06:35 The System Behind the Agent 06:52 Where to Learn More
Not rated yetCustomizing Vertical Voice Agents with ASR and LLM Fine-Tuning | Nemotron Labs
· 52 min
Voice AI experiences are only as good as the models behind them. In this livestream, NVIDIA and our partner expert will walk through how to customize speech and language models to build voice agents for real-world domains and use cases. We'll share practical lessons learned from fine-tuning NVIDIA Nemotron ASR models, including data requirements, training considerations, and techniques for improving recognition accuracy on specialized vocabularies and languages. We'll also explore how post-training and customization can be applied to large language models, and how these approaches can be combined to create domain-specific voice agents. Through real examples and live discussion, attendees will learn: - When and why to fine-tune an ASR model Data, training, and evaluation considerations for speech adaptation - How LLM post-training can improve task-specific performance - How ASR and LLM customization work together in voice-agent workflows - Lessons learned from real-world deployments and experimentation Whether you're building customer service assistants, industry-specific copilots, or multilingual voice applications, this session will provide practical guidance for adapting foundation models to your own use cases.
Not rated yetHow H-Company Optimizes VLM Serving for Computer Use Agents With NVIDIA Dynamo
· 37 min
H-Company's open-source vision is to scale autonomous computer-use agents using transparent foundation models, including the NVIDIA Holo and Holotron model families, and optimized NVIDIA infrastructure. This technical session explores the open architecture behind those agents and shows you how to deploy Holo and Holotron computer-use agentic workloads using NVIDIA Dynamo on NVIDIA GPUs.
Not rated yetNVIDIA NV-Reason-CT: 3D Vision-Language Reasoning for CT Scans
· 2 min
NV-Reason-CT is an open vision-language model that reads chest and abdominal CT scans natively in 3D, reasons through them step by step, and reports what it finds. Most vision-language models were built for 2D images, so with CT they sample a handful of slices or compress the volume into a few tokens before the language model ever sees it. NV-Reason-CT takes a different path: a native 3D vision encoder (Primus 3D ViT) feeds a Qwen3.5-4B language model, trained end to end. All 13,824 visual tokens from each 192×192×192 crop reach the language model, each tagged with its position in 3D. Get started Model on Hugging Face: https://huggingface.co/nvidia/NV-Reason-CT Code and fine-tuning scripts (SFT and GRPO): https://github.com/NVIDIA-Medtech/nv-reason-ct Companion skills for inference and fine-tuning: https://github.com/NVIDIA-Medtech/medical-AI-skills Paper: "NV-Reason-CT: 3D Visual Language Model for CT Analysis": https://arxiv.org/abs/2609.27511 Web demo: https://huggingface.co/spaces/nvidia/nv-reason-ct
Not rated yetWhat's New in CUDA 13.4
· 51 min
CUDA 13.4 brings changes across the toolkit: new CUDA Tile features, new PTX instructions for kernel and library authors, locality-aware APIs for multi-die GPUs, and better GPU sharing for containerized workloads. It also includes a developer preview for the Rubin architecture, so you can target sm_107 and start porting your code before launch. In this livestream, the CUDA team walks through the features most likely to change how you write, tune, and deploy GPU code, with code examples and time for your questions. What you'll learn: - How programmatic dependent launch (PDL) works, and how to use it from cuTile Python and CUDA Tile IR to overlap a kernel’s setup with the end of the kernel before it. - What the new PTX instructions do, including L1 prefetch, int4-to-int8 matrix loads, packed FP8 arithmetic, and lighter-weight proxy fences, and which GPUs they target. - How to start porting to Rubin with the sm_107 developer preview, and how new locality APIs let you keep compute and memory on the same part of a multi-die GPU. - How cgroup-based GPU memory limits and the updated Multi-Process Service (MPS) make it safer to share a GPU across containers, plus updates to cuBLAS, NVCC, and the developer tools. Join us live and bring your questions for the CUDA team.
Not rated yet