Curated sessions engineered for senior practitioners facing heavy production workloads.
Core Systems
Applied ML
Observability
Distributed consensus under failure, storage engine trade-offs, and low-latency networking.
LLM inference at scale, GPU memory management, and training cluster resiliency.
High-cardinality telemetry, real-time anomaly detection, and silent cascading failure modes.
Session Breakdown
08:30 EST - Opening Keynote Post-Mortem
10:15 EST - Track Deep Dives & Teardowns
13:30 EST - Architectural Debates
16:00 EST - Evening Clinics & Workshops
Unfiltered analysis of a major multi-region outage and the systemic architectural flaws that enabled it.
Simultaneous practitioner-led sessions breaking down real production codebases and load failures.
Unscripted cross-functional panel comparing synchronous vs. asynchronous guarantees in high-throughput pipelines.
Hands-on collaborative sessions debugging attendee-submitted production bottlenecks and cluster configurations.
Secure your calendar feed for schedule updates.
Receive direct push notifications when session slides and code repositories go live.