Uploaded June 2026 | Updated September 2026, 3 weeks ago
How do you build a highly scalable, resilient AI platform capable of running machine learning models at massive scale?
In this session from the Builders Track at Cloudflare Immerse Stockholm 2026, Andreas Jansson (Cofounder & CTO at Replicate, and Principal Systems Engineer at Cloudflare) dives deep into the architecture powering Replicate. Discover how they leverage a swarm of cloud agents combined with the power of Cloudflare Workers and edge infrastructure to deploy, scale, and manage complex AI workloads with minimal latency.
Whether you're an AI engineer, a DevOps specialist, or a developer looking to move away from traditional infrastructure, this talk offers practical architectural patterns for building the full AI stack on the edge.
📍 Recorded live at Sergel Hub, Stockholm at Cloudflare Immerse Stockholm 2026.
👉 Learn more about the event: fieldmarketing.www.cloudflare.com/immersestockholm-2026
🕒 TIMESTAMPS:
00:00 - Introduction & The Challenge of Scaling AI
02:15 - What is Replicate? Running Machine Learning at Scale
06:40 - Architecture: Moving Beyond Traditional Containers
12:10 - How a Swarm of Cloud Agents Coordinates Workloads
🚀 RESOURCES & LINKS:
• Build on Cloudflare Workers: workers.cloudflare.com
• Explore Replicate: replicate.com
• Follow Cloudflare Developers on Twitter/X: https://x.com/CloudflareDev
How do you build a highly scalable, resilient AI platform capable of running machine learning models at massive scale?
In this session from the Builders Track at Cloudflare Immerse Stockholm 2026, Andreas Jansson (Cofounder & CTO at Replicate, and Principal Systems Engineer at Cloudflare) dives deep into the architecture powering Replicate. Discover how they leverage a swarm of cloud agents combined with the power of Cloudflare Workers and edge infrastructure to deploy, scale, and manage complex AI workloads with minimal latency.
Whether you're an AI engineer, a DevOps specialist, or a developer looking to move away from traditional infrastructure, this talk offers practical architectural patterns for building the full AI stack on the edge.
📍 Recorded live at Sergel Hub, Stockholm at Cloudflare Immerse Stockholm 2026.
👉 Learn more about the event: fieldmarketing.www.cloudflare.com/immersestockholm-2026
🕒 TIMESTAMPS:
00:00 - Introduction & The Challenge of Scaling AI
02:15 - What is Replicate? Running Machine Learning at Scale
06:40 - Architecture: Moving Beyond Traditional Containers
12:10 - How a Swarm of Cloud Agents Coordinates Workloads
🚀 RESOURCES & LINKS:
• Build on Cloudflare Workers: workers.cloudflare.com
• Explore Replicate: replicate.com
• Follow Cloudflare Developers on Twitter/X: https://x.com/CloudflareDev
