Systems | Development | Analytics | API | Testing

Deploying Gen AI in Production with NVIDIA NIM and MLRun

In this demo, we showcase how to leverage MLRun, Iguazio, and NVIDIA NIMs to deploy and monitor a generative AI model at scale, focusing on reducing risks and ensuring seamless performance. Using NVIDIA's NIMs, the demo demonstrates advanced methods in model monitoring, logging, and continuous fine-tuning.

Balancing Shifting Strategies for Maximum Impact

Are your testing strategies aligned with your team’s goals? Shifting left often requires discipline and advanced skills, making it a safer approach for many teams. On the other hand, shifting right can deliver major rewards if your team has the resources to handle the risks. The key is understanding your team’s capabilities and aligning your strategy with your specific goals, whether that means prioritizing safety or speed.

A Visionary Future with Enterprise GenAI

An overview of how GenAI empowers Cloudera customers to drive impactful business outcomes, and how Cloudera AI makes it easier for organizations to deploy and scale AI successfully. We dive into powerful tools like Accelerators for Machine Learning Projects (AMPs), Cloudera AI Inference service, AI Assistants, and end-to-end GenAI platforms, all designed to accelerate your AI journey.

Deploying Your Own Helix Core Server on AWS

Want to set up your own Helix Core server in the cloud? In this video Jase Lindgren, Senior Solutions Engineer at Perforce Software, provides a step-by-step guide to deploying and configuring your own Helix Core server on AWS. To get started: Select AWS Cloud to get the free cloud template link.

How Testing Strategies Differ by Industry

Testing isn’t one-size-fits-all—it depends on your industry and tolerance for risk. Shipping updates every few seconds might work for Amazon, but is it right for your industry? On Test Case Scenario, we break down why testing strategies vary so much depending on context. For example: Banks prioritize careful testing to protect transactions and avoid costly errors. Companies like Amazon rely on razor’s-edge testing, monitoring traffic patterns to spot issues fast.