---
title: "Inference performance as a competitive advantage"
category: "talks"
date: "2026-06-30"
time: "2:50pm-3:10pm"
track: "Expo Stage 1 NE"
room: "Expo Stage 1 NE"
speakers: ["Alex Campos", "Yunmo Koo"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: ""
scheduleRoom: "Expo Stage 1 NE"
scheduleLabels: ["Expo Stage 1 NE", "session", "confirmed"]
---
# Inference performance as a competitive advantage

## Conference Context
- Date/time: 2026-06-30 · 2:50pm-3:10pm
- Track/room: track TBD · Expo Stage 1 NE
- Speaker(s): Alex Campos, Yunmo Koo
- Session type/status: session · confirmed

- Track: track TBD
- Room: Expo Stage 1 NE
- Session type: session
- Status: confirmed

## Session Description
Most AI teams focus on model quality, but production success often comes down to inference performance. In this session, FriendliAI will explore the optimization techniques behind high-performance LLM serving, including continuous batching, speculative decoding, smart caching, and efficient GPU utilization. Learn how leading AI teams reduce infrastructure costs, improve latency, and scale inference workloads without sacrificing performance. We'll share practical insights and deployment strategies that separate experimental AI projects from production-grade systems.Whether you're an ML engineer, platform engineer, MLOps practitioner, or technical founder, you'll leave with a better understanding of how inference optimization can become a competitive advantage for your AI applications.

## Media Evidence
No related AI Engineer channel video found yet.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## People
- [[alex-campos]]
- [[yunmo-koo]]

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# Inference performance as a competitive advantage ## Conference Context - Date/time: 2026-06-30 · 2:50pm-3:10pm - Track/room: track TBD · Expo Stage 1 NE - Speaker(s): Alex Campos, Yunmo Koo - Session type/status: session · confirmed - Track: track TBD - Room: Expo Stage 1 NE - Session type: session - Status: confirmed ## Session Description Most AI teams focus on model quality, but production success often comes down to inference performance. In this session, FriendliAI will explore the optimization techniques behind high-performance LLM serving, including continuous batching, speculative decoding, smart caching, and efficient GPU utilization. Learn how leading AI teams reduce infrastructure costs, improve latency, and scale inference workloads without sacrificing performance. We'll share practical insights and deployment strategies that separate experimental AI projects from production-grade systems.Whether you're an ML engineer, platform engineer, MLOps practitioner, or technical founder, you'll leave with a better understanding of how inference optimization can become a competitive advantage for your AI applications.

### Speaker And Company Context
- [[alex-campos|Alex Campos]] — Director of Sales Partnerships at [[friendliai|FriendliAI]].
- [[yunmo-koo|Yunmo Koo]] — Founding Engineer at [[friendliai|FriendliAI]].

### Topics Covered
- Topic links are pending transcript-backed classification.

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.