Cerebras Hot Seat: Angela Yeung on Scaling AI Hardware

In this episode of Cerebras Hot Seat, Angela Yeung sits down to discuss the architectural breakthroughs and engineering challenges of scaling compute for modern AI workloads. We dive deep into hardware optimization, wafer-scale performance, and what it takes to break through current compute bottlenecks. Key Topics Covered: 00:00 - Introduction & Welcome 01:15 - Engineering at Wafer Scale 04:30 - Overcoming AI Hardware Bottlenecks 08:45 - The Future of Compute Architecture 11:20 - Closing Thoughts & Key Takeaways Learn More About Cerebras: Explore Cerebras Technology: https://cerebras.ai Follow us on Twitter/X: https://x.com/CerebrasSystems Connect on LinkedIn: https://www.linkedin.com/company/cerebras-systems