MetaRoCE for AI Infrastructure on Ethernet
MetaRoCE for Ethernet-based AI infrastructure: how Meta moves intelligence into the NIC, eliminates PFC, and creates a loss-resilient transport for million-GPU scale.
AI Security in Production: Roblox Prompt to Prod
AI Security in Production at Roblox: how sandboxing, guardrails, and exemplars help safely lead AI agents from prompt to production.
Alloy central gateway: how to avoid dropping the telemetry stream
A central gateway for full telemetry: sizing, load testing, HPA, WAL, and GOMEMLIMIT in a production scenario—with no blind spots.
Automated RCA in microservices at Atlassian
Automated RCA in microservices turns metrics, logs, and traces into ranked root cause hypotheses for faster incident validation and cleaner diagnosis
AWS Aurora and DynamoDB for AI Context
Data replication for AI agents: how Aurora, DynamoDB, and Keyspaces help avoid stale reads, race conditions, and context errors.
Remote Spectre attack on Cloudflare Workers
remote Spectre attack on Cloudflare Workers: how DyPrIs, V8 Sandbox, and in-process isolation reduced the risk of memory leakage in production.
Git fetch in CI: how Datadog alleviated CPU from a bottleneck
Git fetch in CI became a bottleneck. An analysis of the gitretriever architecture at Datadog, CPU reductions, relay models, and APIs for code queries.
Container security Swift: zero-touch on hundreds of clusters
Container security at Swift: how zero-touch automation, central scanning, and regression testing reduced noise and simplified protection for hundreds of clusters.
eBPF for AI API: control without code changes
eBPF for AI API in Kubernetes: how to intercept traffic, limit AI agents, and control behavior without code changes and container restarts.
Swift container security without manual noise
Container security at Swift: how centralized architecture, automated scans, and regression testing reduced manual noise in hybrid cloud.