USENIX Courses

DADI - Block-Level Image Service for Agile and Elastic Application Deployment

Explore DADI, a block-level image service enhancing application deployment agility and elasticity. Learn about its instant container start, peer-to-peer architecture, and multi-runtime support.

• YouTube
• 21 minutes
• On-Demand
• Conference Talk

On Adaptive Attacks to Adversarial Example Defenses

Explore adaptive attacks on adversarial example defenses, examining challenges, whitebox attacks, and key observations to understand vulnerabilities in machine learning security.

• YouTube
• 20 minutes
• On-Demand
• Conference Talk

Inside NVIDIA’s AI Infrastructure for Self-Driving Cars

Explore NVIDIA's Project MagLev, an AI platform for self-driving car development, covering data management, neural network training, and large-scale validation across petabytes of data.

• YouTube
• 26 minutes
• On-Demand
• Conference Talk

Scalable AutoML for Time Series Forecasting Using Ray

Explore scalable AutoML for time series forecasting using Ray, covering feature generation, model selection, and distributed hyper-parameter tuning with real-world applications and insights.

• YouTube
• 22 minutes
• On-Demand
• Conference Talk

Managing ML Models at Scale - Intuit’s ML Platform

Explore Intuit's ML Platform for scalable, secure model lifecycle management using GitOps, SageMaker, Kubernetes, and Argo Workflows. Learn about feature management, cost optimization, and enterprise-level ML model deployment.

• YouTube
• 26 minutes
• On-Demand
• Conference Talk

Ten Persistent SRE Antipatterns - Pitfalls on the Road to a Successful SRE Program

Explore common pitfalls in Site Reliability Engineering and learn strategies to build successful SRE programs, drawing insights from industry leaders like Netflix and Google.

• YouTube
• 54 minutes
• On-Demand
• Conference Talk

Making the Most of Your SRE Toolbox - Bootstrapping Your SRE Team through Reuse

Explore strategies for repurposing existing tools and frameworks to establish an effective SRE organization, drawing from real-world experiences in building comprehensive delivery pipelines.

• YouTube
• 39 minutes
• On-Demand
• Conference Talk

Principles of Chaos Engineering

Explore principles of Chaos Engineering to improve resilience in distributed systems. Learn techniques for surfacing inherent chaos and building confidence in system behavior at scale.

• YouTube
• 53 minutes
• On-Demand
• Conference Talk

I'm an SRE Lead! Now What? How to Bootstrap and Organize Your SRE Team

Practical guide for new SRE leads on organizing teams, managing expectations, and implementing effective strategies. Covers phased approaches, lessons learned, and pitfalls to avoid in SRE journey.

• YouTube
• 52 minutes
• On-Demand
• Conference Talk

DNSControl - A DSL for DNS as Code from StackOverflow.com

Explore DNSControl, a DNS DSL and compiler enabling DevOps practices for DNS management. Learn how StackOverflow.com automates complex configurations, simplifies updates, and enhances reliability.

• YouTube
• 40 minutes
• On-Demand
• Conference Talk

Opaque - An Oblivious and Encrypted Distributed Analytics Platform

Explore Opaque, a distributed analytics platform offering strong security for sensitive data through encryption, authentication, and oblivious operators, with optimized performance on Spark SQL.

• YouTube
• 26 minutes
• On-Demand
• Conference Talk

Live Video Analytics at Scale with Approximation and Delay-Tolerance

Explore VideoStorm, a system for efficient live video analytics at scale, featuring resource management techniques to optimize quality and lag for thousands of concurrent queries.

• YouTube
• 27 minutes
• On-Demand
• Conference Talk

Clipper - A Low-Latency Online Prediction Serving System

Explore Clipper, a low-latency prediction serving system that enhances machine learning deployment with improved latency, throughput, accuracy, and robustness across various frameworks and applications.

• YouTube
• 26 minutes
• On-Demand
• Conference Talk

VFP - A Virtual Switch Platform for Host SDN in the Public Cloud

Explore Microsoft Azure's Virtual Filtering Platform (VFP), a programmable virtual switch for host SDN in public clouds. Learn its design, API, flow language, and real-world performance in large-scale deployments.

• YouTube
• 27 minutes
• On-Demand
• Conference Talk

Efficient Memory Disaggregation with Infiniswap

Explore INFINISWAP: an RDMA-based remote memory paging system that improves application performance by leveraging unused cluster memory, without modifying existing applications or OS.

• YouTube
• 24 minutes
• On-Demand
• Conference Talk