InfoQ Homepage Conferences Content on InfoQ
-
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)
-
Enchant Your AI and APIs with eBPF Magic 🪄
Dan Finneran explains how to use eBPF and AI gateways in Kubernetes to transparently observe, modify, and control unowned AI agent API calls without altering source code.
/presentations/ebpf-ai-gateway-kubernetes-security/en/mediumimage/dan-finneran-medium-1786539181222.jpeg)
-
Why Fetch When You Can Sync? Building Local-First Apps on a Sync Engine Architecture
James Arthur explains how extending reactivity to the server via Electric and TanStack DB replaces manual data fetching with real-time sync for high-performance, agentic web applications.
/presentations/local-first-sync-engine/en/mediumimage/James-Arthur-medium-1786620651340.jpeg)
-
Understanding Progressive Collapse: How To Avoid A Cascading Failure
Sam Newman explains how to apply civil engineering’s concept of progressive collapse to digital systems, sharing actionable techniques to mitigate cascading failures in complex cloud architecture.
/presentations/progressive-collapse-system-resilience/en/mediumimage/sam-newman-medium-1785845419904.jpg)
-
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)
-
Turning Outward: Growing From Code to Influence
Brad Grantham explains how senior engineers and architects can transition from writing code to building influence by sharpening communication, mastering business alignment, and empowering teams.
/presentations/working-across-teams/en/mediumimage/BradGrantham-medium-1786538733504.jpg)
-
From Thousands to One: Building LLM-Powered Selection Systems
Jendrik Jördening explains how to build reliable LLM architecture by enforcing strict schemas, separating AI text reasoning from deterministic code, and applying automated output validation.
/presentations/architecture-patterns-llm/en/mediumimage/JendrikJordening-medium-1786535626643.jpeg)
-
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 Right 300 Tokens Beat 100k Noisy Ones: The Architecture of Context Engineering
Baruch Sadogursky and Patrick Debois explain context engineering antipatterns in coding agents, demonstrating how skills, right-tool retrieval, and external memory optimize developer workflows.
/presentations/architecture-context-engineering/en/mediumimage/partick-baruch-medium-1786008501700.jpg)
-
Migrating Uber Eats Feeds to Webview
Nick DiStefano discusses how Uber Eats migrated core mobile surfaces to a hybrid WebView stack, sharing insights on maintaining native UI quality and shipping features faster.
/presentations/migration-mobile-application/en/mediumimage/nickdistefano-medium-1785845098133.jpg)
-
Adopting Memory-Safety and Fine-Grained Compartmentalisation with CHERI
David Chisnall explains how CHERI architecture unifies hardware capabilities and pointer metadata to deliver memory safety and fine-grained, efficient software compartmentalization.
/presentations/cheri-memory-safety-compartmentalization/en/mediumimage/DavidChisnall-medium-1785845255636.jpg)
-
Producing the World's Cheapest Tokens: A How-to Guide
Meryem Arik explains how to cut AI inference costs by up to 90% by optimizing batch sizes, hardware selection, and request scheduling for high-volume, non-real-time workloads.
/presentations/ai-token-price/en/mediumimage/meryem-arik-medium-1785844873071.jpg)