CEOInterviews.AI
Start App
Try: AI strategy tariffs earnings guidance layoffs interest rates growth

Saurabh Dighe

Corporate Vice President, Azure Hardware Systems, Microsoft

Search every verified Saurabh Dighe interview, podcast appearance, and on-the-record quote — each transcript cross-checked by AI and human review to confirm speaker identity. Saurabh Dighe, Corporate Vice President of Azure Hardware Systems at Microsoft, discussed the company's Maia 300 AI accelerator in an October 2026 podcast appearance. He described the system as a fully co-designed architecture focused on addressing the "data movement problem" in AI inference, rather than treating it solely as a compute challenge. Dighe detailed the chip's TSMC N2P chiplet design, which enables 18 TB/s of HBM4 memory bandwidth through a memory interface chiplet that expands the die to support eight HBM modules. He stated that the transition from HBM3E to HBM4 improves data transfer rates and power efficiency per bit. Dighe also noted that Microsoft uses AI agents for automated kernel optimization as part of its full-stack approach to maximize "intelligence per watt and per dollar." Dighe said Microsoft's Maia 200 is currently in production and "outperforming some of the GPUs" in the company's fleet. He announced plans to scale Maia deployments to multi-gigawatt capacity starting in 2027, describing this as a "very important strategic positioning" for Microsoft and a key component of its products and services.

Recent appearances

  • AI Inference Is a Data Movement Problem: Microsoft's Saurabh Dighe on the Maia 300

    Microsoft's Maia 300 is a fully co-designed system, optimized to solve the memory-bound "data movement problem" of emerging agentic AI workloads. Saurabh Dighe, Corporate VP of Azure Hardware Systems at Microsoft, sits down with Austin to detail the architecture, from its TSMC N2P chiplet design enabling 18 TB/s of HBM4 memory bandwidth to its use of AI agents for automated kernel optimization. They discuss how this full-stack approach aims to maximize intelligence per watt and per dollar for Microsoft's planet-scale services. This episode is presented by @CrusoeAI. Crusoe's Serverless Fi…

    Watch on YouTube ↗

  • An Interview with Microsoft's Saurabh Dighe About Maia 200

    Maia 100 was a pre-GPT accelerator. Maia 200 is explicitly post-GPT for large multimodal inference. Saurabh Dighe says if Microsoft were chasing peak performance or trying to span training and inference, Maia would look very different. Higher TDPs. Different tradeoffs. Those paths were pruned early to optimize for one thing: inference price-performance. That focus drives the claim of ~30% better performance per dollar versus the latest hardware in Microsoft’s fleet. Topics covered: • What “30% better price-performance” actually means • Who Maia 200 is built for • Why Microsoft bet on inferen…

    Watch on YouTube ↗

Other executives at Microsoft

The summary and quote tags on this profile are produced with AI assistance from verified, first-person interview transcripts, then checked by our team to confirm the speaker's identity and the accuracy of every quote. See how we verify →