The Five-Layer Cake Approach to Scaling AI Without Wasting Money

The Five-Layer Cake Approach to Scaling AI Without Wasting Money

Author: Demetrios September 4, 2026 Duration: 38:55

In this episode of Agentic Conversations, we sit down with Ambud Sharma, Principal Engineer at Pinterest, responsible for general technology efficiency, fresh off delivering a controversial keynote on AI infrastructure optimization at scale.


Ambud walks us through his Five Layer Cake framework - a structured approach to driving efficiency across every level of the AI stack, from silicon and hardware procurement to model selection, inference engine design, and governance. We explore how decisions compound across layers to unlock real business growth, and how the wrong choices can lock you into expensive commitments for years.


We stress test the framework against two very different business models: what the stack looks like if you are building the next Cursor, and how it changes entirely if you are building the next YouTube. Along the way we cover hardware immutability, inference engine warm-up costs, GPU occupancy, context switching, quantization trade-offs, model routing, and why experimentation discipline is the only thing that keeps AI infrastructure costs from getting out of control.


We also look at how this framework holds up in the emerging agent era, what changes when agent-to-agent communication becomes the norm, and why agent traffic just passed bot traffic on Cloudflare. The conversation closes on a deceptively simple takeaway: there is no silver bullet, and experimentation at every layer always comes first.


Pinterest: https://about.pinterest.com/


Alex Salkever: https://www.linkedin.com/in/alexsalkever

Ambud Sharma: https://www.linkedin.com/in/ambud


Timestamps:

[0:00] Introduction and the controversial keynote

[2:09] The five-layer cake explained

[4:30] Why hardware decisions are irreversible

[6:47] Two business models: building Cursor vs YouTube

[10:42] Applying the five layers to a YouTube-style company

[14:23] Experimentation as the core efficiency method

[17:09] Inference stack: context switching and warm-up costs

[20:07] Model layer: why changing models breaks everything

[24:10] When you should not use an LLM at all

[26:41] Governance and routing: right model for the right task

[29:20] Horror stories of unchecked token spend

[31:37] Experimentation discipline without stifling innovation

[34:35] How the five layers change in the agent era

[36:05] Agent-to-agent communication and governance complexity

[38:27] Core takeaway: experimentation first at every layer


Hosted by Demetrios, MLOps.community is a space for honest, meandering talks about the real work of making artificial intelligence systems actually work. This isn't about hype or theoretical papers; it's about the messy, practical, and often surprising journey of taking models from a notebook into a live environment. You'll hear from engineers and practitioners who are in the trenches, discussing the tools, the frustrations, and the occasional breakthroughs that define the day-to-day. The conversations are deliberately relaxed, covering everything from traditional machine learning pipelines to the new world of large language models and even the intangible "vibes" of team culture and process. Each episode peels back a layer on what "production" really means, whether that involves deploying a predictive service, managing an agentic system, or maintaining reliability as everything scales. Tuning into this podcast feels like grabbing a coffee with colleagues who aren't afraid to dig into the technical nitty-gritty while keeping the tone conversational and accessible. It's for anyone who builds, manages, or is just curious about the operational backbone that allows AI to deliver value, offering a grounded perspective often missing from the broader conversation.
Author: Language: en-us Episodes: 50

Agentic Conversations (formally mlops.community)
Podcast Episodes
Skills over MCP on the streets of Tokyo [not-audio_url] [/not-audio_url]

Duration: 32:30
Tool descriptions tell an agent what a tool does. They don't tell it how to use five tools together, in the right order, following your conventions. That gap is where this conversation lives.Filmed at AGNTCon + MCPCon in…
Walking Tokyo Talking Agent Protocols [not-audio_url] [/not-audio_url]

Duration: 28:49
Two people, a wrong turn into a back alley, a community garden, and about thirty minutes of arguing about protocols on the streets of Tokyo.The guest is Angie Jones, VP of Developer Experience at the Agentic AI Foundatio…
Why Cost Per Million Tokens Is A Useless KPI? [not-audio_url] [/not-audio_url]

Duration: 38:49
A year ago, Palo Alto Networks built dashboards to track AI spend. Today those dashboards are useless, and the team that built them thinks that's the whole story.Recorded at FinOps X in San Diego, this conversation bring…
The Winchester Mystery House Problem in AI Development [not-audio_url] [/not-audio_url]

Duration: 59:41
AI models are starting to act like appliances, locked into one narrow way of working, instead of the flexible infrastructure they used to be. Drew Breunig, an AI and data strategist working with the Overture Maps Foundat…
How Predictive Analytics Stops Budget Overruns Before They Happen? [not-audio_url] [/not-audio_url]

Duration: 29:23
Every engineer at Wayfair can now see, in real time, exactly what their code costs, and that's on purpose. Brent Eubanks, FinOps Architect at Wayfair, walks us through what happens when you stop treating AI spend as a fi…
How To Delegate To An Agent Like You Would An Employee? [not-audio_url] [/not-audio_url]

Duration: 55:15
OpenAI's Codex developer experience lead sits down with a former comedian turned ML engineering lead for a conversation about what happens when computer use agents stop being a novelty and start actually running your day…
Why Your AI Bill Will Double Before It Gets Better [not-audio_url] [/not-audio_url]

Duration: 32:24
In this episode, we're joined by Josh Collier, FinOps Lead at Superhuman (formerly Grammarly), to explore what it really costs to run AI at scale and why the rules of the game changed faster than anyone expected.We discu…
MCP Goes Stateless [not-audio_url] [/not-audio_url]

Duration: 52:27
David Soria Parra is an Engineering Lead at Anthropic and one of the core maintainers of the Model Context Protocol (MCP). We explore the biggest evolution of the protocol since its launch, and why MCP is becoming the fo…
AI Hype vs. Real Value [not-audio_url] [/not-audio_url]

Duration: 42:37
Manish Dasaur is a Managing Director at PwC with over 20 years in data and AI, having helped 100+ clients navigate AI disruption and extract real business value from data, AI, and agentic AI initiatives. In this episode,…
The Creator of FastMCP Explains the Future of MCP [not-audio_url] [/not-audio_url]

Duration: 55:11
In this episode, we're joined by Jeremiah Lowin, Founder & CEO at Prefect and the creator of FastMCP, to explore how one of the most influential projects in the MCP ecosystem came to be - and where the protocol is headin…