AI Systems Design
Design systems for LLM serving, inference optimisation, and vector DB at scale.
0%
Confidence · no data yet
After this skill you can…
- Design an LLM inference cluster with vLLM
- Implement batching and caching strategies for LLM APIs
- Architect a production RAG system for millions of queries
Prerequisites
Watch (10 videos)
Explore NVIDIA Metropolis AI-Powered Multi-Camera Tracking on AWS
→ Deploy AI-powered tracking on cloud infrastructure→ Configure multi-camera tracking workflow
Accelerate AI on NVIDIA RTX AI PCs with Windows ML | Microsoft Build 2025
→ Build AI applications with Windows ML→ Deploy AI models on NVIDIA RTX AI PCs
Generative AI web development with Angular
→ Build generative AI web apps→ Deploy AI models to production
Dassault Systèmes 3DEXCITE accelerates product experiences with AWS cloud solutions
→ Design cloud-based product development workflows→ Deploy personalized customer experiences
End-to-End AI: From Development to Deployment
→ Deploy AI applications at the edge→ Manage AI systems with Fleet Command
How Nuro transformed end-to-end AI and data discovery with Google Cloud Consulting
→ Design scalable infrastructure for AI→ Implement data discovery solutions
Demo - Create Azure AD app to work with groups using Microsoft Graph
→ Register Azure AD applications for Microsoft Graph→ Submit requests to Microsoft Graph for group management
How to develop AI apps easily using Gemini, Vertex AI, Firebase, and Flutter
→ Build AI apps with Gemini and Vertex AI→ Integrate Firebase and Flutter for AI app development
How to build Visual AI Agents with NVIDIA Cosmos Reason and Metropolis
→ Build Visual AI Agents with NVIDIA Cosmos Reason→ Post-train Cosmos Reason with custom data
[Workshop] AI Pipelines and Agents in Pure TypeScript with Mastra.ai — Nick Nisi, Zack Proser
→ Build AI pipelines with Mastra.ai→ Create internal AI assistants with composable tools
Read (10 articles)
📄
DeepCamp AI