MLOps Community
+00:00 GMT
Building Robust AI Systems with Battle-tested Frameworks
LIVESTREAM

Building Robust AI Systems with Battle-tested Frameworks

# LLMs
# AI Deployment
# Data Pipelines

AI systems don’t just need to be intelligent—they need to be reliable and resilient in real-world applications. This session brings together experts who have tackled the toughest challenges in AI deployment, from shipping production-ready LLMs to building fault-tolerant data pipelines.

🔹 Breaking the Demo Barrier and Getting Agents Shipped – Learn how to make LLMs production-ready with structured prompting, dynamic routing, and error-handling strategies. Discover why JSON might be holding back your model's accuracy!

🔹 Failure is Always an Option: What Apollo Can Teach Us About Resilient Data Pipelines – Take lessons from NASA’s Apollo mission to build resilient and self-healing data pipelines that won’t fail under pressure.

🔹 Modal: ML Infra That Does Not Suck – Building an application on the cloud doesn’t have to be painful—even when using GPUs and foundation models! This talk introduces Modal, the serverless Python infrastructure you didn’t know you always wanted.

Whether you're working on AI-driven apps, data pipelines, or pushing the boundaries of structured outputs, this session will equip you with battle-tested strategies to take your AI systems from demo to deployment.

Don’t miss out—join us live!

Speakers

Ben Epstein
Ben Epstein
- @ -
Vaibhav Gupta
Vaibhav Gupta
CEO @ Boundary ML
Brendan O'Leary
Brendan O'Leary
VP, Developer Relations @ Prefect
Charles Frye
Charles Frye
AI Engineer @ Modal Labs

Agenda

5:00 PM, GMT
-
5:05 PM, GMT
Opening / Closing
Introduction
Ben Epstein
5:05 PM, GMT
-
5:20 PM, GMT
Presentation
Breaking the Demo Barrier and Getting Agents Shipped

Deploying Large Language Models (LLMs) in production brings a host of challenges well beyond prompt engineering. Once they're live, even the smallest oversight—like a malformed API call or unexpected user input—can cause failures you never saw coming. In this talk, Vaibhav Gupta will share proven strategies and practical tooling to keep LLMs robust in real-world environments. You'll learn about structured prompting, dynamic routing with fallback handlers, and data-driven guardrails—all aimed at catching errors before they break your application.

You'll also hear why the naïve use of JSON can reduce a model's accuracy, and discover when it's wise to push back on standard serialization in favor of more flexible output formats. Whether you're processing 100+ page bank statements, analyzing user queries, or summarizing critical healthcare data, you'll not only understand how to prevent LLMs from failing but also how to design AI-driven solutions that scale gracefully alongside evolving user needs.

+ Read More
Vaibhav Gupta
5:20 PM, GMT
-
5:35 PM, GMT
Presentation
Failure is Always an Option: What Apollo Can Teach Us About Resilient Data Pipelines

”1202 ALARM! 1202 ALARM!” These words from Buzz Aldrin during Apollo 11’s lunar descent weren’t a crisis announcement - they were proof that Margaret Hamilton’s resilient software design worked exactly as intended. When faced with an overflow of data, the Apollo Guidance Computer prioritized critical tasks and kept going, ultimately landing humans on the moon with just seconds of fuel remaining.

Today’s data pipelines face similar challenges: complex systems, distributed dependencies, and high-stakes outcomes where failure is inevitable. As data workflows evolve from monolithic ETL jobs into distributed microservices, they demand the same resilience patterns that revolutionized application development. This talk explores how the lessons from Apollo - from Hamilton’s priority scheduling to NASA’s rigorous engineering mindset - directly inform modern data engineering practices and are embodied in Prefect 3.0’s transactional orchestration.

+ Read More
Brendan O'Leary
5:35 PM, GMT
-
5:50 PM, GMT
Presentation
Modal: ML Infra That Does Not Suck

Building an application on the cloud doesn't have to suck. Even if it uses GPUs and foundation models! In this talk, I'll present Modal, the serverless Python infrastructure you didn't know you always wanted.

+ Read More
Charles Frye
5:50 PM, GMT
-
5:55 PM, GMT
Panel Discussion
Q & A
5:55 PM, GMT
-
6:00 PM, GMT
Opening / Closing
Closing
Event has finished
March 26, 5:00 PM, GMT
Online
Organized by
MLOps Community
MLOps Community
Event has finished
March 26, 5:00 PM, GMT
Online
Organized by
MLOps Community
MLOps Community