<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Aws on AI Engineer Guide</title><link>https://aiengineerguide.com/tags/aws/</link><description>Recent content in Aws on AI Engineer Guide</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright © 2024-2026, Nesin Technologies LLP.</copyright><lastBuildDate>Tue, 23 Jun 2026 22:52:49 +0530</lastBuildDate><atom:link href="https://aiengineerguide.com/tags/aws/feed.xml" rel="self" type="application/rss+xml"/><item><title>AWS Lambda Gets MicroVM Support for Sandboxed Code Execution</title><link>https://aiengineerguide.com/til/aws-lambda-microvm/</link><pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate><guid>https://aiengineerguide.com/til/aws-lambda-microvm/</guid><description>&lt;p>AWS now has support for running untrusted code similar to model.com, Vercel Box, etc called &lt;a href="https://aws.amazon.com/lambda/lambda-microvms/">AWS Lambda MicroVM&lt;/a>&lt;/p>
&lt;p>It is powered by &lt;a href="https://firecracker-microvm.github.io/">Firecracker&lt;/a> the same tech which powers AWS Lambda.&lt;/p>
&lt;p>&lt;img src="https://cdn.qblog.nesin.io/f_auto,q_auto/qblog/AIEngineerGuide/2026-06/ml02vf0cbrtuj6tedout" alt="2026-06-23-at-22.49.50.png">&lt;/p>
&lt;p>The main problem it tries to solve is running &lt;strong>AI generated code&lt;/strong> without having to worry about the security.&lt;/p>
&lt;blockquote>
&lt;p>Each MicroVM gives a single end user or session its own isolated environment that launches rapidly, retains memory and disk state for the length of the session, and pauses to a low idle cost when the user steps away.&lt;/p></description></item></channel></rss>