InfoQ Homepage Machine Learning Content on InfoQ
-
Beyond the Prototype: Scaling Framework Agnostic AI Agent Infrastructure with Ray
The speakers explain how to run and autoscale LLM agents in production using Ray, detailing system architecture, control planes, multi-region deployments, and CI/CD pipelines with LLM evals.
/presentations/scale-llm-agents-production-ray/en/mediumimage/medium-1792065446239.jpg)
-
Ontology‐Driven Observability: Building the E2E Knowledge Graph at Netflix Scale
Prasanna Vijayanathan and Renzo Sanchez-Silva explain how Netflix uses AIOps, AI agents, and operational ontologies to turn high-scale telemetry into automated, proactive incident root-cause analysis.
/presentations/netflix-observability-aiops-ontology-scale/en/mediumimage/medium-1790845339712.jpg)
-
Building Reusable Evaluation Frameworks for Agentic AI Products
Susan Chang shares how Elastic built a production-grade AI agent evaluation framework, detailing lessons on tracing, LLM-as-a-judge, programmatic evals to prevent regression across engineering teams.
/presentations/elastic-ai-agent-evaluations/en/mediumimage/susan-chang-medium-1790846586191.jpeg)
-
Building GenAI Platform at DoorDash
Swaroop Chitlur and Sidd Kodwani explain how DoorDash built and scaled an enterprise GenAI platform, revealing key architectural bets, pivots, and operational principles driving real business impact.
/presentations/doordash-genai-platform-architecture/en/mediumimage/SiddharthKodwaniSwaroopChitlur-medium-1790246592519.jpg)
-
Adaptive Recommenders in the Real World: Inference, Evals, and System Design
Mallika Rao shares why building adaptive recommendation systems requires shifting focus from isolated ML models to real-time feedback loops, retrieval freshness, and production-level constraints.
/presentations/adaptive-recommendation-systems-architecture/en/mediumimage/mallika-medium-1789632229433.jpeg)
-
From S3 to GPU in One Copy: Rethinking Data Loading for ML Training
Onur Satici discusses Vortex, an open-source columnar file format designed to bypass CPU bottlenecks, enabling ultra-fast S3-to-GPU data streaming and dynamic query pruning at up to 60 Gbps.
/presentations/vortex-columnar-file-format-gpu-streaming/en/mediumimage/onur-satici-medium-1787813397611.jpeg)
-
Running AI at the Edge: Running Real Workloads Directly in the Browser
James Hall explains why engineering teams should shift AI workloads on-device. He shares local inference strategies, WebGPU optimization techniques, and architecture choices for zero-trust privacy.
/presentations/local-ai-browser-inference-privacy/en/mediumimage/james-hall-medium-1787813225372.jpeg)
-
SafeChat: Building AI-Powered Safety Systems at Scale in a Real-Time Marketplace
Bruna Pereira shares how DoorDash built a scalable AI moderation platform. Learn how combining cheap classifiers with LLM scoring reduced incidents and cut latency in real-time chat.
/presentations/doordash-llm-ai-moderation-platform/en/mediumimage/bruna-pereira-medium-1786539036040.jpeg)
-
From Fab To Token - The State Of The Market
Jordan Nanos explains how hardware constraints, data center scale, and chip co-design shape modern AI performance and tokenomics from silicon to inference.
/presentations/ai-hardware-tokenomics/en/mediumimage/jordan-nanos-medium-1786538855211.jpg)
-
From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash
Sudeep Das explains how DoorDash transforms e-commerce recommendations using LLM-driven semantic consumer memory, hierarchical semantic IDs, grounded agentic search, and multi-tiered LLM ranking.
/presentations/ai-agentic-recommendations-semantic-ids/en/mediumimage/sudeep-das-medium-1785845550765.jpeg)
-
The Infrastructure Challenge behind Production AI
The panelists share how core data systems and cloud platforms handle machine-driven workloads, exploring infrastructure design patterns and failure points as AI becomes a permanent fixture.
/presentations/ai-infrastructure-scaling-architecture/en/mediumimage/infoq-live-medium-1782888285223.jpg)
-
Reimagining Platform Engagement with Graph Neural Networks
Mariia Bulycheva explains how Zalando utilized Graph Neural Networks to move beyond tabular data, modeling higher-order user-item interactions to optimize long-term engagement and click probability.
/presentations/graph-neural-networks/en/mediumimage/Mariia-Bulycheva-medium-1775048997053.jpeg)