InfoQ Homepage AI, ML & Data Engineering Content on InfoQ
-
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.
-
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.
-
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.
-
Leveraging Adversary Emulation for GenAI Red Teaming
Kennedy Torkura explains how to apply GenAI red teaming to secure AWS Bedrock models and knowledge bases, leveraging MITRE ATLAS to discover cloud supply chain vulnerabilities.
-
Keeping ChatGPT Fast as AI Development Accelerates
Martin Spier shares how agentic coding accelerates release velocity at OpenAI and explains how always-on AI agents redefine performance engineering to keep ChatGPT fast at massive scale.
-
Rewriting All of Spotify's Code Base, All the Time
Aleksandar Mitic and Jo Kelly-Fenton discuss how Spotify uses "Honk," a background AI coding agent, to automate codebase migrations at scale and tackle the ongoing maintenance problem.
-
From ms to µs: OSS Valkey Architecture Patterns for Modern AI
Dumanshu Goyal explains how moving from proxied architectures to direct access in Redis/Valkey slashes tail latency to microseconds, lowers costs, and eliminates single points of failure.
-
The Five Stages of AI Maturity in Engineering Organizations - Where and Why Teams Get Stuck
Quotient CEO Lizzie Matusov explores why surging enterprise AI spend isn't driving faster software delivery, introducing a 5-stage AI maturity framework to unblock bottlenecks across the SDLC.
-
Architecting AI Systems for the Messy Reality of Enterprises: Why Agentic Compute is the Missing Layer
Arun Joseph explains how to successfully build and deploy enterprise-grade agentic platforms by leveraging existing teams, JVM stacks, and a "compute as the agent" architectural paradigm.
-
Getting Rid of LeetCode Interviews in the World of AI
Daniel Doubrovkine shares why LeetCode interviews are obsolete in the AI era and discusses how engineering leaders must adapt hiring loops to evaluate real-world system design and AI collaboration.
-
The Future of Engineering: Mindsets That Matter When Code Isn’t Enough
Ben Greene shares lessons from startups for software engineers navigating AI coding agents. He explains why starting simple, keeping comprehension, and prioritizing customer impact matter.
-
Autonomous Data Products for the Autonomous Era: Rethinking Data Architecture for GenAI
Jörg Schad discusses how to bridge the gap between prototypes and production by standardizing data access for GenAI, using autonomous data products to prevent context rot and ensure safety.