> Markdown version of [/videos/world-congress-2026-north-america?page=15](https://www.wearedevelopers.com/videos/world-congress-2026-north-america?page=15). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Videos 2651 videos · 28490 moments · 1454.1 hours of content ## World Congress North America 2026 videos ### Know Your Enemies: Live Exploit of a PHP Engine Security Breach Did you know a single null byte can compromise millions of systems? Watch a live PHP engine exploit to expose the hidden vulnerabilities lurking in your foundational infrastructure. - **Speakers:** Alexandre Daubois - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 30:04 - [Watch](https://www.wearedevelopers.com/videos/100502-know-your-enemies-live-exploit-of-a-php-engine-security-breach) ### Real-Time Data Platforms at Trillion-Event Scale Adding just 100 microseconds to a task can inflate cloud bills by millions. Learn to architect real-time data platforms that survive trillion-event scales through extreme computational efficiency. - **Speakers:** Diptamay Sanyal - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 26:39 - [Watch](https://www.wearedevelopers.com/videos/100478-real-time-data-platforms-at-trillion-event-scale) ### Agentic Drift: keeping pace with your agents Are AI agents deploying code faster than you can review it? Discover how to combat agentic drift and transition your engineering team from manual reviews to systemic governance. - **Speakers:** Colleen Lake - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 19:58 - [Watch](https://www.wearedevelopers.com/videos/100453-agentic-drift-keeping-pace-with-your-agents) ### Edge AI: Running Agentic Intelligence Where Internet Can't Reach How do you run agentic AI when the internet fails? Small language models now orchestrate secure, real-time reasoning entirely offline. Master building hybrid architectures that thrive anywhere. - **Speakers:** Nitin Eusebius - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 21:19 - [Watch](https://www.wearedevelopers.com/videos/100434-edge-ai-running-agentic-intelligence-where-internet-can-t-reach) ### Compute for your AI model: GPUs, LPUs, TPUs and beyond.. Is your shared hardware starving your AI model's decode phase? Learn to slash inference latency using disaggregated serving across specialized GPUs, TPUs, and SRAM-dense LPUs. - **Speakers:** Kushaagra Goyal - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 24:02 - [Watch](https://www.wearedevelopers.com/videos/100417-compute-for-your-ai-model-gpus-lpus-tpus-and-beyond) ### Designing High-Performance AI APIs: Lessons from Serving Millions of Real-Time Requests Wayne Liu warns that standard REST APIs fail under heavy AI inference. Discover how asynchronous, task-based orchestration seamlessly powers 200 million daily requests for retail giants. - **Speakers:** Wayne Liu - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 28:50 - [Watch](https://www.wearedevelopers.com/videos/100365-designing-high-performance-ai-apis-lessons-from-serving-millions-of-real-time-requests) ### From transaction sequences to pricing decisions at 140M+ customer scale What if you treated financial transactions like natural language? Discover how Nubank uses transformer models to automate complex credit pricing decisions for over 140 million customers. - **Speakers:** Hiroto Udagawa - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 10:34 - [Watch](https://www.wearedevelopers.com/videos/100571-from-transaction-sequences-to-pricing-decisions-at-140m-customer-scale) ### Acquired Live Interview: Justin Boitano (VP, Enterprise AI Products, NVIDIA) Justin Boitano reveals how fine-tuned open-source AI now outperforms proprietary frontier models. Discover how NVIDIA's kernel-level infrastructure enables organizations to safely orchestrate millions of autonomous enterprise agents. - **Speakers:** Justin Boitano, Ben Gilbert, David Rosenthal - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 27:52 - [Watch](https://www.wearedevelopers.com/videos/100369-acquired-live-interview-justin-boitano-vp-enterprise-ai-products-nvidia) ### The Autonomous Performance Agent: A Netflix Production Story Netflix built an autonomous agent that continuously profiles live services and proposes validated code fixes. Discover how to automate performance optimization and intercept inefficiencies before they deploy. - **Speakers:** Rajat Shah - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 11:20 - [Watch](https://www.wearedevelopers.com/videos/100585-the-autonomous-performance-agent-a-netflix-production-story) ### The New Security Stack If an autonomous agent goes rogue at 3 a.m., who gets the phone call? Discover why generative AI demands a completely redesigned zero-access security stack. - **Speakers:** Javier Garza, Sagi Rodin, Andrea Muttoni, James Everingham, Kara Sprague - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 29:59 - [Watch](https://www.wearedevelopers.com/videos/100607-the-new-security-stack) ### How AI Agents Tripled Our Test Coverage on a 1.8M-Line iOS Codebase What happens when your AI coding agent tries to cheat CI? Discover how Duolingo built strict guardrails to autonomously triple unit test coverage on a 1.8-million-line iOS codebase. - **Speakers:** Kush Agrawal - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 27:13 - [Watch](https://www.wearedevelopers.com/videos/100523-how-ai-agents-tripled-our-test-coverage-on-a-1-8m-line-ios-codebase) ### Understanding LLM Architectures: Inside the Design of Modern Models Treating LLMs as static black boxes introduces significant production risk. Master underlying mechanics like MoE and KV caching to optimize your real-world memory latency and system throughput. - **Speakers:** Jofia Jose Prakash - **Event:** World Congress 2026 North America - **Published:** September 24, 2026 - **Duration:** 25:38 - [Watch](https://www.wearedevelopers.com/videos/100477-understanding-llm-architectures-inside-the-design-of-modern-models) [Next page](https://www.wearedevelopers.com/videos/world-congress-2026-north-america?page=16)