---
title: "Kevin Orellana"
category: "people"
role: "Software Engineer"
company: "Amazon Web Services"
linkedin: "https://www.linkedin.com/in/kevinorellana/"
twitter: "https://x.com/KevssOrellana"
sourceLabels: ["Official speaker roster", "Official conference schedule"]
---
# Kevin Orellana

## Profile
Software Engineer at [[amazon-web-services|Amazon Web Services]].

- [LinkedIn](https://www.linkedin.com/in/kevinorellana/)
- [X / Twitter](https://x.com/KevssOrellana)

## Biography
Kevin Orellana is a software engineer at AWS, where he builds the sandboxed code-execution and browser-automation infrastructure that lets AI agents — including coding agents — run code and drive websites safely at scale. He previously worked on Amazon Bedrock's model-serving platform, where he tech-led the launch of Anthropic's Claude Sonnet on Bedrock and helped design the infrastructure behind several frontier-model launches.

## Conference Sessions
- [[2026-06-30-kevin-orellana-1-000-agent-tasks-in-a-sandbox-what-breaks-when-llms-write-and-run-code]] — 1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Write and Run Code (2026-06-30, 2:25pm-2:45pm)

## Evidence Graph
This evidence graph summarizes how this person appears across the conference source graph: scheduled sessions, linked videos, transcripts, and slide-derived evidence.

### Linked Sessions
- [[2026-06-30-kevin-orellana-1-000-agent-tasks-in-a-sandbox-what-breaks-when-llms-write-and-run-code|1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Write and Run Code]]

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