InfoQ - Machine Learning https://www.infoq.com InfoQ Machine Learning feed Presentation: Running AI at the Edge: Running Real Workloads Directly in the Browser https://www.infoq.com/presentations/local-ai-browser-inference-privacy/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Machine+Learning <img src="https://res.infoq.com/presentations/local-ai-browser-inference-privacy/en/mediumimage/james-hall-medium-1787813225372.jpeg"/><p>James Hall discusses the strategic and technical imperative of moving AI workloads from cloud providers to local edge devices. He shares practical approaches using WebGPU, Transformers.js, and DuckDB to achieve near-native performance in JavaScript. Through real-world case studies, he explains how to minimize data privacy risks, optimize browser inference, and build rigorous evaluation suites.</p> <i>By James Hall</i> AI Security Cloud Computing GPU Web Browser QCon London 2026 Privacy Edge Computing Machine Learning Web Development Local Inference Transcripts AI, ML & Data Engineering Architecture & Design Development presentation Mon, 31 Aug 2026 11:00:00 GMT https://www.infoq.com/presentations/local-ai-browser-inference-privacy/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Machine+Learning James Hall 2026-08-31T11:00:00Z /presentations/local-ai-browser-inference-privacy/en Presentation: SafeChat: Building AI-Powered Safety Systems at Scale in a Real-Time Marketplace https://www.infoq.com/presentations/doordash-llm-ai-moderation-platform/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Machine+Learning <img src="https://res.infoq.com/presentations/doordash-llm-ai-moderation-platform/en/mediumimage/bruna-pereira-medium-1786539036040.jpeg"/><p>Bruna Pereira explains how DoorDash built a content-agnostic AI moderation platform. She covers replacing costly LLM-only pipelines with a hybrid pattern: using fast internal models to filter obvious cases, LLM multi-axis scoring for nuanced decisions, and no-code workflows with backtesting. Discover how this architectural pattern cut safety incidents while scaling to millions of daily messages.</p> <i>By Bruna Pereira</i> Agents QCon AI Boston 2026 AI Architecture Large language models Cost Optimization Real-Time Data Machine Learning Platform Engineering Transcripts AI, ML & Data Engineering Architecture & Design Development presentation Sat, 22 Aug 2026 11:00:00 GMT https://www.infoq.com/presentations/doordash-llm-ai-moderation-platform/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Machine+Learning Bruna Pereira 2026-08-22T11:00:00Z /presentations/doordash-llm-ai-moderation-platform/en