Your AI infrastructure is only as effective as your visibility into it, and right now, most teams are flying blind. In this hands-on workshop, you’ll learn how to use real-time observability to reduce costs, eliminate waste, and keep your AI Factory running at peak performance. We’ll dive into practical techniques to:
- Identify GPU underutilization, throttling, and idle capacity across both cloud and on-premises deployments before they burn through your budget.
- Monitor token usage for inference workloads (including NVIDIA NIM containers) to catch cost spikes and inefficiencies as they happen.
- Correlate slow inference jobs or degraded model performance to root-cause issues anywhere in the stack, so you can fix problems without throwing more hardware or cloud spend at them.
Through live demonstrations, you’ll see how real-time telemetry and AI-driven correlation turn raw metrics into immediate, actionable insights, helping you cut unnecessary spend, speed up troubleshooting, and ensure your models deliver maximum value. If you’re responsible for making AI infrastructure faster, leaner, and more cost-efficient, this is the one workshop you can’t afford to miss.
Devin Avery
Devin Avery brings over 20 years of experience in software engineering, specializing in enterprise and service provider software development. Currently serving as Product Development Architect at Virtana, he is driving the company’s approach for AI Factory Observability, Generative AI capabilities, and Infrastructure Observability. His career includes previous principal software engineering roles at Brocade and software engineering roles at CA Technologies, establishing a solid foundation in developing complex enterprise solutions.
Devin has a proven track record of designing and delivering scalable, high-quality software solutions through a disciplined, iterative, and use-case-driven design and testing philosophy. He holds multiple patents for his work on algorithms related to applying collection policies, traversing topologies, and testing abstractions. With a Bachelor of Science in Computer Science from the University of New Hampshire, Devin has a keen ability to decompose high-level user requirements into executable stories and effectively bridge the gap between development teams and product management. His skills have been instrumental in transforming legacy products into modern, customer-centric solutions.
Virtana
Website: https://www.virtana.com/
Virtana is the leader in hybrid infrastructure observability, helping enterprises maximize the performance and efficiency of their most demanding AI workloads. Our AI Factory Observability (AIFO) platform delivers real-time, full-stack visibility across GPUs, compute, network, storage, data fabric, application, orchestration, training, and inference—whether on-premises, in the cloud, or in hybrid environments.
With AIFO, organizations can pinpoint GPU underutilization, detect bottlenecks, and track token usage across inference workloads (including NVIDIA NIM containers) to eliminate waste and control costs. Our AI-driven correlation engine connects performance issues directly to root causes, enabling teams to troubleshoot in real time instead of overprovisioning hardware or cloud resources.
Trusted by global enterprises to manage complex, large-scale environments, Virtana empowers AI infrastructure teams to cut costs, accelerate workloads, and ensure reliable, high-performance AI at scale.
Learn more at Virtana.com — or visit us at the AI Infra Summit at booth #830 to see AIFO in action.
