SpotifyWhy We Use Separate Tech Stacks for Personalization and Experimentation
Explores why Spotify separates personalization ML and experimentation tooling to build scalable, low-latency recommendations using contextual bandits and RL-powered models across teams.
SalesforceMigration at Scale: Moving Marketing Cloud Caching from Memcached to Redis at 1.5M RPS Without Downtime
Zero-downtime migration of Marketing Cloud caching from Memcached to Redis Cluster at 1.5M RPS across 50+ applications, preserving millisecond latency and enabling proactive hot-key management.
Google CloudInstant insights: Gemini CLI's New Pre-Configured Monitoring Dashboards
Gemini CLI now ships with pre-configured Google Cloud Monitoring dashboards and OpenTelemetry-powered telemetry, delivering out-of-the-box visibility into usage, performance, and logs with minimal setup.
LyftLyft’s Feature Store: Architecture, Optimization, and Evolution
Lyft's Feature Store architecture and optimization: a platform-of-platform data system unifying batch, online, and streaming features, with governance, low-latency serving, and lifecycle tooling to accelerate ML at scale.
LyftLyft’s Feature Store: Architecture, Optimization, and Evolution
Lyft’s Feature Store architecture combines batch, streaming, and online serving to unify feature management, detailing optimization, governance, and developer-friendly improvements that scale ML for a rideshare platform.
SalesforceScaling Sales Agents: Engineering Next-Gen AI for the Enterprise Era
Scaling from a single Engagement Agent MVP to a dispatcher-driven, enterprise-scale multi-agent platform that delivers high-throughput, fair, and observable AI-powered outreach at scale.
CloudflareA closer look at a BGP anomaly in Venezuela
Comprehensive analysis of a Venezuela BGP route-leak involving AS8048 (CANTV), examining probable routing-policy misconfigurations and highlighting ASPA and RFC9234 as paths toward a safer, more verifiable BGP ecosystem.
Apple MLNarrativeTrack: Evaluating Video Language Models Beyond the Frame
NarrativeTrack introduces a benchmark for evaluating temporally grounded narrative understanding in multimodal language models, using entity-centric reasoning and a Compositional Reasoning Progression framework that scales from entity existence to changes and ambiguity.
Apple MLImproving User Interface Generation Models from Designer Feedback
A designer-aligned pipeline for improving UI generation models that leverages feedback via commenting, sketching, and direct manipulation to finetune LLMs with multimodal data and human evaluations, outperforming traditional RLHF baselines.
DatabricksInstructed Retriever: Unlocking System-Level Reasoning in Search Agents
Introducing the Instructed Retriever, a system-aware retrieval architecture that propagates system specifications (user instructions, labeled examples, and index schema) through query generation and retrieval to enable robust instruction-following, low-latency enterprise agent search.
Google CloudReflecting on a year of transformation and mission impact together
One-year retrospective on Google Public Sector's AI-enabled cloud, security-first innovations, and agentic technologies like Gemini that accelerate government missions across defense, civilian agencies, and education.
Jane StreetFun with Algebraic Effects - from Toy Examples to Hardcaml Simulations
A practical guide to replacing monads with algebraic effects in OCaml 5, using the Handled_effect library to implement clean, composable Hardcaml FPGA testbenches and simulations.