سیستمهای توزیعشده و یادگیری ماشین در مقیاس اوبر.
Discover how Uber is performing vertical CPU autoscaling for stateful workloads across a server fleet with large CPU performance differences. Correctly handling these differences ensures we have a both efficient and reliable platform at Uber.
Dive into how Uber’s Legal Team is leveraging Agentic AI to help lawyers review contracts faster, flag risks, and improve every negotiation.
Uber has embraced MCP to supercharge AI powered developer workflows with quality context. Learn how Uber scaled from a community driven solution to hundreds of MCP servers.
Discover how Uber engineered a highly scalable feature logging pipeline to ensure data consistency for training/serving and boost performance for large scale models. MachineLearning MLOps UberEngineering DataEngineering Scaling
What if retries could know when they’re helping, and when they’re making things worse? Uber Engineering built error ownership to prevent and contain retry storms.
Mapping the invisible: Uber’s novel approach to learning critical service dependencies at scale.
Every millisecond of latency is a lost opportunity—especially when people are hungry. 🍔 We cut Uber Eats search latency in half by re architecting our full stack pipeline. Read our latest deep dive to see how we did it.
Explore how and why Uber redesigned its Kubernetes® scaling control plane to coordinate multiple orchestrators, improve failover efficiency, and stay reliable at scale.
Reducing operational blast radius in distributed systems is a constant challenge. Learn how our new subclustered placement algorithm for M3DB limits shard migration impact, enables safer parallel operations, and improves predictability as our clusters scale. DistributedSystems DatabasePerformance UberEngineering
We just published a deep dive on how we keep AI coding costs under control at Uber, even as usage keeps climbing. Since February, weekly active employees across all functions on our agentic offerings grew 7x, and weekly agent requests grew 9.4x. Over that same stretch, total spend has relatively stabilized. We broke…
Discover how Uber uses ApacheHudi column stats and table sorting to optimize GCS storage costs and egress, and improve latency for selective DSAR and privacy compliance export workloads. Engineering DataLakehouse CloudOptimization ApacheSpark Parquet
Discover the core principles behind Uber’s Payments Platform, built 10 years ago, and how they’ve powered Uber’s growing $217B ARR business.
How many unique users did Uber serve this quarter? For mission critical metrics like these, we had the standard engineering answer: approximate. Learn how we solved for getting an exact count at scale. DataEngineering BigData ApacheSpark Uber DistributedSystems
