54 articles
Airbnb migrated its identity graph from third-party PaaS to an internally-managed knowledge graph infrastructure built on JanusGraph and DynamoDB.
Viaduct 1.0 represents Airbnb's evolution from internal tool to production-ready, community-driven data mesh platform.
This article presents testing methods to measure and improve AI agent skill invocation reliability using Pinterest's internal agents and Claude Code.
This paper presents a Contextual Sequential Two-Tower Model for Pinterest ads that integrates real-time context into sequential recommender systems.
This post explains how Airbnb eliminated circular dependencies in its observability stack to ensure reliable monitoring at scale.
Pinterest optimized ML serving network efficiency by implementing Feature Trimmer to reduce bandwidth bottleneck.
Skipper is Airbnb's embedded workflow engine designed to enable durable execution of multi-step business processes without requiring external orchestration infrastructure.
Pinterest built an ML model optimizing shopping conversions by addressing sparse offsite conversion events.
Airbnb built a metrics storage system ingesting 50 million samples per second and storing 1.3 billion active time series.
Pinterest's MIQPS algorithm automatically learns which URL parameters affect content identity, enabling efficient deduplication across millions of merchant URLs at scale.
Pinterest engineers debugged why Ray-based ML training jobs were crashing with intermittent network connectivity issues on Kubernetes clusters backed by AWS EC2.
Airbnb introduces privacy-first social features for Airbnb Experiences, separating internal user data from public profiles to protect guest privacy while enabling social connections.
Pinterest shares their technique of request-level deduplication to manage infrastructure costs when scaling recommendation systems with 100x increased model parameters.
Pinterest's approach to automatically measuring user-perceived latency (Visually Complete) on Android surfaces by embedding measurement logic into base UI classes.
This post details a production migration of a large-scale metrics pipeline from StatsD to OpenTelemetry (OTLP) with Prometheus-based storage and vmagent for streaming aggregation.
This article discusses Pinterest's evolution of the multi-objective optimization layer in their home feed recommendation system.
This article tells the career story of Jonathan Woodard, a former professional NFL defensive end who transitioned into software engineering and joined Airbnb's Secure Development Engineering team.
Airbnb explains how COVID broke their booking-to-trip forecasting models and the architectural changes they built to handle structural data shifts.
Pinterest describes how they built a production MCP (Model Context Protocol) ecosystem to enable AI agents to safely automate engineering tasks.
Airbnb shares hard-won lessons from migrating its observability platform from third-party vendors to a custom in-house solution built on Prometheus across 1,000 services.
Pinterest