Skip to main content
The TWIML AI Podcast

How to Engineer AI Inference Systems with Philip Kiely - #766

54 min episode · 2 min read
·
Philip Kiely

Episode

54 min

Read time

2 min

Topics

Remote Work, Artificial Intelligence, Software Development

AI-Generated Summary

Key Takeaways

  • Inference research-to-production timeline: New inference techniques move from research paper to production implementation in hours, not weeks. Base Ten's team implemented a PoloQuant CUDA kernel 31 hours after the paper published. Engineers should monitor inference research continuously, as techniques dismissed a year ago can become immediately viable when model scales shift.
  • Product maturity deployment cycle: Companies follow a predictable inference path: start with per-token closed APIs, then move to hyperscaler provisioned throughput (AWS Bedrock, GCP Vertex), then dedicated inference providers like Base Ten with weight-owned models, then in-house platforms. The trigger is typically cost overruns or capacity constraints, not company size.
  • KV cache prefix optimization: A single token difference early in a prompt sequence invalidates the entire KV cache, eliminating reuse benefits. Engineers should structure system prompts and chat templates to maximize shared prefixes across requests, ensuring cache hits. This applies regardless of whether inference runs on owned infrastructure or third-party providers.
  • Task-model matching for agentic speed: Agents making hundreds of model calls per user action require specialized runtimes per task type. Running named entity recognition on a frontier LLM costs significantly more versus a specialized runtime. Base Ten's NER runtime runs in 1 millisecond versus 500 milliseconds on a small LLM — a 500x difference that eliminates visible latency in agent pipelines.
  • Hopper GPU staying power: H100 rental prices are higher now than a year ago despite Blackwell availability. Hopper GPUs remain dominant because open-source models from Chinese labs are optimized for Hopper architecture due to export controls, and smaller models (1–8B parameters) run efficiently on MIG-partitioned Hopper slices without requiring full Blackwell NVL72 systems.

What It Covers

Philip Kiely, Head of AI Education at Base Ten, explains inference engineering as a discipline requiring expertise across CUDA programming, distributed systems, and applied research. He covers the maturity cycle from per-token APIs to dedicated deployments, hardware generations, and why inference optimization becomes critical at scale for agentic AI workloads.

Key Questions Answered

  • Inference research-to-production timeline: New inference techniques move from research paper to production implementation in hours, not weeks. Base Ten's team implemented a PoloQuant CUDA kernel 31 hours after the paper published. Engineers should monitor inference research continuously, as techniques dismissed a year ago can become immediately viable when model scales shift.
  • Product maturity deployment cycle: Companies follow a predictable inference path: start with per-token closed APIs, then move to hyperscaler provisioned throughput (AWS Bedrock, GCP Vertex), then dedicated inference providers like Base Ten with weight-owned models, then in-house platforms. The trigger is typically cost overruns or capacity constraints, not company size.
  • KV cache prefix optimization: A single token difference early in a prompt sequence invalidates the entire KV cache, eliminating reuse benefits. Engineers should structure system prompts and chat templates to maximize shared prefixes across requests, ensuring cache hits. This applies regardless of whether inference runs on owned infrastructure or third-party providers.
  • Task-model matching for agentic speed: Agents making hundreds of model calls per user action require specialized runtimes per task type. Running named entity recognition on a frontier LLM costs significantly more versus a specialized runtime. Base Ten's NER runtime runs in 1 millisecond versus 500 milliseconds on a small LLM — a 500x difference that eliminates visible latency in agent pipelines.
  • Hopper GPU staying power: H100 rental prices are higher now than a year ago despite Blackwell availability. Hopper GPUs remain dominant because open-source models from Chinese labs are optimized for Hopper architecture due to export controls, and smaller models (1–8B parameters) run efficiently on MIG-partitioned Hopper slices without requiring full Blackwell NVL72 systems.

Notable Moment

Kiely describes how text-to-speech models have a hard ceiling of roughly 80–100 tokens per second for real-time audio output. Beyond that threshold, the optimization goal flips entirely — engineers should increase batch size for concurrent streams or reduce hardware costs rather than chasing higher token throughput.

Know someone who'd find this useful?

Episode Transcript

Mean, it might be the fastest timeline in the world. If you think about medicine, for example, it can take decades for research to reach a pharmacy. If you think about, you know, physics or engineering, it can take years to apply a new concept. Even within AI, if you want to train a model off of a new technique, it can still take weeks or months to find the exact right way to sort of express that technique. But with inference, the timeline is often hours. A new model architecture comes out. You have to figure out how to support it day zero. Alright, everyone. Welcome to another episode of the TwiML AI podcast. I am your host, Sam Sherrington. Today, I'm joined by Philip Kiley. Philip is head of AI education at Base ten. Before we get going, be sure to take a moment to hit that subscribe button wherever you're listening to today's show. Phillip, great to see you again, and welcome to the podcast. Hey, Sam. Thanks for having me on. Absolutely. Absolutely. We met at, the recent GTC conference where you were signing copies of that book that you have there, over your, I guess, your left shoulder. Yeah. The And I've got one here on my desk in front of center now. There you go. That was a really fun conference. I I felt like, like a rock star, you know, just, like, handing out. We also had honestly, I think part of it was we had free ice cream at the booth as well. Uh-huh. And, I gave away a lot of books, but I did run the numbers at the end of the show. The ice cream was more popular. You know, I I thought, it'd be good to get you on and talk through, like, you know, a little bit about, you know, inference engineering, you know, what what you're writing about in the book, but also kinda what you're seeing beyond the book and, what is really kinda making a difference from, you know, inference perspective nowadays. So before we get to that, though, I'd love to have you talk a little bit about, you know, your journey, like, what brought you to, you know, Base 10 and inference engineering. So back in 2022, this was ten months before ChatGPT was launched to the public. I had a a really strong and novel thesis about the AI industry. That strong and novel thesis was I need a job. And so I, I applied for a bunch of jobs and I ended up choosing between Base ten and a laundry delivery startup. And it was, like, a really tough decision, because it's hey. It's it's a good the other one's a good company to show around. But ultimately, I I decided to go work on some some really interesting problems in the ML space with a tiny startup at the time called called Base ten. And I've been at it for …

Get the full transcript (8,612 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all The TWIML AI Podcast transcripts →

You just read a 3-minute summary of a 51-minute episode.

Get The TWIML AI Podcast summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • by Amazon Web Services

    Companies follow a predictable inference path: start with per-token closed APIs, then move to hyperscaler provisioned throughput (AWS Bedrock, GCP Vertex), then dedicated inference providers like Base Ten with weight-owned models
  • by Google Cloud

    Companies follow a predictable inference path: start with per-token closed APIs, then move to hyperscaler provisioned throughput (AWS Bedrock, GCP Vertex), then dedicated inference providers like Base Ten with weight-owned models

company

  • Philip Kiely, Head of AI Education at Base Ten, explains inference engineering as a discipline requiring expertise across CUDA programming, distributed systems, and applied research.

More from The TWIML AI Podcast

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's AI & Machine Learning Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into The TWIML AI Podcast.

Every Monday, we deliver AI summaries of the latest episodes from The TWIML AI Podcast and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime