Join us for an Ask Me Anything with the Foundry Local team on September 29th, 2025!

Discover how Foundry Local is redefining edge AI with powerful features like on-device inference, enabling you to run models directly on your hardware, cutting costs and keeping your data secure. Whether you're customizing models to fit unique use cases or integrating seamlessly via SDKs, APIs, or CLI, Foundry Local offers scalable pathways to Azure AI Foundry as your needs evolve. It's the perfect solution for environments with limited connectivity, sensitive data requirements, low-latency demands, or early-stage experimentation before cloud deployment. If you're building smarter, leaner, and more private AI workflows, this AMA is your chance to dive deep with the team behind it all.

What is Foundry Local?

Foundry Local is a set of development tools designed to help you build and evaluate LLM applications on your local machine. It provides a curated collection of production-quality tools, including evaluation and prompt engineering capabilities, that are fully compatible with Azure AI. This allows for a seamless transition of your work from your local environment to the cloud. Don't miss this opportunity to connect with our experts and enhance your understanding of local LLM development.

Foundry Local is an on-device AI inference solution offering performance, privacy, customization, and cost advantages. It integrates seamlessly into your existing workflows and applications through an intuitive CLI, SDK, and REST API.

Key features

• On-Device Inference: Run models locally on your own hardware, reducing your costs while keeping all your data on your device.
• Model Customization: Select from preset models or use your own to meet specific requirements and use cases.
• Cost Efficiency: Eliminate recurring cloud service costs by using your existing hardware, making AI more accessible.
• Seamless Integration: Connect with your applications through an SDK, API endpoints, or the CLI, with easy scaling to Azure AI Foundry as your needs grow.

How to Join:

Register to Join the Azure AI Foundry Discord Community Event
29th Sept 2025
9am Pacific Time UTC−08:00

Unlock Accelerated Local LLM Development

Discover how Foundry Local can enhance your development process and explore the possibilities for building robust LLM applications. Whether you're a seasoned AI developer or just getting started, this session is your chance to get hands-on insights into the innovative world of Azure AI Foundry.

Event Highlights:

• An in-depth overview of the Foundry Local CLI and SDK.
• Interactive demo with step-by-step examples.
• Best practices for local AI Inference and models
• Transitioning your local development to cloud solutions or vice-versa

Why Attend?

• Gain expert insights into Foundry Local, and ask questions about using Foundry Local
• Network with fellow AI professionals and developers.
• Enhance your AI development skills with practical examples.
• Stay at the forefront of LLM application development. 

Speakers

Maanav Dalah
Product Manager Foundry Local

Maanav Dalal 

Product Manager |Foundry Local 
Microsoft

Maanav Dalal is a PM on the AI Frameworks team. He's super inquisitive about the ways you use AI in daily life, so be encouraged to strike up a conversation with him about that.

LinkedIn Profile

Brandon interviews Michael Irwin, Principal Engineer at Docker. They cover Docker’s evolution, why hardened images matter, and how AI fits in. Plus, Michael shares stories from teaching computer science.

Watch the YouTube Live Recording of Episode 538

Show Links

• Docker
• Docker Hub

Contact Michael

• LinkedIn: mikesir87
• Github: mikesir87
• Twitter: mikesir87
• Blog: https://blog.mikesir87.io/

Sponsor

• Docker: Your foundation for secure, intelligent development

SDT News & Hype

• Join us in Slack.
• Get a SDT Sticker! Send your postal address to stickers@softwaredefinedtalk.com and we will send you free laptop stickers!
• Follow us: Twitch, Twitter, Instagram, Mastodon, BlueSky, LinkedIn, TikTok, Threads and YouTube.
• Use the code SDT to get $20 off Coté’s book, Digital WTF, so $5 total.
• Become a sponsor of Software Defined Talk!

Special Guest: Michael Irwin.

Sponsored By:

• Docker: Docker: Your foundation for secure, intelligent development

Download audio: https://aphid.fireside.fm/d/1437767933/9b74150b-3553-49dc-8332-f89bbbba9f92/5d314acc-4047-423a-b140-e3f58edbc4b5.mp3

Join us for an insightful conversation with Mike Davis, Engineering Manager, and Rob Nelson, VP of Engineering at Zilch, a leading UK-based buy now pay later platform. Discover how this cloud fintech scaled from a monolithic architecture to a sophisticated microservices ecosystem serving 5 million customers. Learn about their journey migrating from MSSQL to Aurora, their innovative use of AWS services including EKS, SNS/SQS for event-driven architecture, and API Gateway for WebSocket connections. The discussion explores their unique implementation of push notifications, in-app messaging, and how they leverage generative AI for merchant discovery. Get a behind-the-scenes look at their fraud detection system using Kinesis and Flink, and hear about their upcoming physical card launch.

With Robert Nelson, VP of Engineering, Zilch ; With Mike Davis, Engineering Manager, Zilch

Watch this episode on video

Download audio: https://op3.dev/e/dts.podtrac.com/redirect.mp3/developers.podcast.go-aws.com/media/182.mp3

In just two more weeks, the pricing for TechBash 2025 increases. We are currently in the Standard Pricing period, but starting on October 4th, pricing will increase $100 for all ticket types during the Late Bird Pricing period. So, what are you waiting for? Register today at techbash.com.

TechBash 2025, held November 4–7 at Kalahari Resorts in Pocono Manor, PA, is packed with forward-thinking content for developers. This year’s keynotes include Nicole Tibaldi’s talk, “Eat Your Vegetables: Prioritizing the Health of Your Engineering Team,” which explores how to advocate for essential but often deprioritized engineering tasks like documentation and test coverage. Kevin Griffin will also deliver a keynote on the State of the .NET Foundation and .NET Open Source, joined by Microsoft’s Jeff Fritz to discuss community involvement and new projects within the .NET ecosystem.

The workshop lineup is equally robust, offering deep dives into CI/CD with GitHub Actions and Azure DevOps Pipelines, Dependency Injection in C#, PostgreSQL for SQL Server developers, and practical applications of off-the-shelf AI tools. There’s even a full-day container and Kubernetes workshop for those looking to master cloud-native infrastructure. These workshops are designed to be hands-on and immediately applicable, making them ideal for developers aiming to level up their skills.

Across three full days of sessions, attendees will explore topics spanning web development, cloud architecture, DevOps, best practices, and soft skills. With over 70 sessions and dozens of world-class speakers—including Microsoft MVPs and industry veterans—TechBash promises a dynamic and inclusive learning environment. Whether you’re a seasoned engineer or attending your first developer conference, TechBash offers a rare blend of technical depth and community spirit.

Get more information about our speakers, sponsors, hotel rooms, and more on techbash.com.

The event takes place at the Kalahari Resort and Convention Center in Pocono Manor, PA, home of the second largest, indoor water park in North America. Get your room at the Kalahari starting at just $169 a night for each night you choose to stay between Monday, November 3rd and Friday, November 7th

Want to send your dev team? Reach out to TechBash to ask about discounts for groups of five or more.

AWS has announced the integration of LocalStack with the AWS Toolkit for Visual Studio Code, addressing a long-standing challenge in serverless development where developers needed to juggle multiple tools and complex configurations for local testing of event-driven applications.

By Claudio Masolo

In this podcast, Shane Hastie, Lead Editor for Culture & Methods, spoke to Shannon Mason about optimizing team productivity by understanding the neuroscience behind cognitive load, distinguishing between beneficial "slack time" and detrimental "idle time", and how the pursuit of maximum utilization that leads to burnout and poor decision-making.

By Shannon Mason