Michael Levan
Building High-Performing Agentic and Kubernetes Environments | AI Architect & Forward Deployed Engineer | AAIF & CNCF Ambassador | 4x Published Author & International Public Speaker
Saddle Brook, New Jersey, United States
Actions
Michael Levan translates technical complexity into practical value. He is a Principal AI Architect and Forward Deployed Engineer in the AI and Platform Engineering space who spends his time working with organizations around the globe on technical implementation and strategy. Michael is also a Microsoft MVP, 4x published author, podcast host, international public speaker, AAIF Ambassador, CNCF Ambassador, and was part of the Kubernetes v1.28 and v1.31 Release Team.
Links
Your Production-Ready OSS AI Assistant
Interacting with LLMs, MCP Servers, Agent Skills and Agents help you do everything from troubleshoot your environment, build new environments, and build real-world application stacks.
And the best part is that it can all be done in open-source!
In this session, you will learn how to build your very own AI Engineering Assistant that can help you with any task you can think of from troubleshooting an environment to building out a new stack, all autonomously and right from your terminal or your phone.
The stack that you use is all open-source, runs in Kubernetes, and can have the ability to perform any action you set your mind to.
Cost & Token Optimization For Agentic and MCP
LLMs and MCP Server tools are at the forefront of every engineering organization when it comes to agentic implementation. That's why there are two major questions that come up.
1). How can we observe metrics, OTel data, and usage.
2) How can we control cost.
Traditional monitoring falls short for AI workloads. Organizations are extending platforms like OpenTelemetry for AI specifically so they can pinpoint failures and hallucinations in LLM interactions along with token usage to understand costs. When using a proper AI Gateway, organizations can accomplish the implementation needs for these needs.
In this session, you'll learn how to use agentgateway to produce Agentic and MCP traffic to get a visualization on what is going on within the environment at the observability level.
From Black Box to See-Through: Observing and Troubleshooting Agentic Infrastructure
When it comes to performance optimization, monitoring, and observability, the stakes are changing. Instead of thinking about CPU, memory, or bandwidth, engineers are being asked to figure out cost based on Token usage and LLM call observability. The way that observabiity works and more importantly, what data matters, is fundamentally different in the world of AI.
How engineers look at an environments performance has always been the same (look at logs/traces/metrics) and same rules will apply in the world of agentic infrastructure except now, instead of looking at a standard environment or application, engineers will be combing body-based responses and LLM usage.
This session will showcase how to reinvent the way we look at performance optimization and observability within environments using kagent, an open-source tool designed to run AI Agents declaratively and natively on Kubernetes.
Plugging Security Holes in LLMs and MCP Servers: Insight From 2,000 Customer Calls
In over 2,000 customer calls in the past year around AI, the two major conversation points are:
1. Securing Agentic infrastructure, MCP Server connectivity (for both users and Agents), and ensuring a proper AI Gateway exists to secure/observe traffic.
2. Access Control and OAuth for connecting to MCP Servers and LLMs.
With both stdio (like libraries/modules) and streamable http (an MCP Server sitting in someones environment), organizations need to ask themselves how they're implementing auth at both the system and user level to access these MCP servers (and from the Agents), what tools are exposed from the MCP Servers, and how the tunnel (from user/agent to MCP Server) is observed and secured.
When organizations are implementing LLM providers, the same thought comes into mind - who can use these LLMs and what are they able to do with the access?
In this session, you'll learn how to plug security holes by understanding the current standards (stdio and streamable http), authentication at both the system and user level (jwt, oAuth, and OIDC), where an AI gateway can help secure traffic throughout the tunnel, and how to specify what tools should be exposed from MCP Servers with traffic policies.
2,000+ Customer Calls About AI In Production - Here's What You Need To Know
An Architect in Applied AI means being on 20+ calls per week with customers implementing AI in production. These are customers ranging from the largest telecom providers in the world to the largest banks worldwide, healthcare, retail, and organizations across the globe. The calls range from discovery to mapping out architecture to AI implementation and everything in between.
Within all of those calls over months at a time, there's a vast amount of information that's collected to fully understand how AI can, and should, be implemented for any company in the world.
In this session, I'm going to go over the top 5 things that every organization asks for when implementing anything Agentic, regardless of the sector they're in.
The topics will include:
1. Agent and agentic network security around AI Gateways, MCP, LLMs, and Agent Skills.
2. Agent quality output (evals and deterministic behavior).
3. Authentication and authorization with standard OIDC/iDP practices along with OAuth, ReBAC and ABAC.
3. Multi-agent architectures.
5. Cost and performance optimization when thinking about tokens, caching, and inference.
The goal of this session is for everyone to be able to leave knowing exactly what organizations are looking to implement when it comes to Agentic today, so everyone can prepare to do the same, or similar, based on current production AI needs.
Sandboxed Agents: Building Isolated, Governed and Scalable AI
Agents need to be isolated for what they can and can't access (files/folders, production envs, LLMs, MCP tools, runtimes, etc. - think autonomous and standard Agents) and at the same time, scale up and down based on load, if/how the Agent is being used, and how it's being used.
By default, Agents have access to every file, LLM, command, and authN/Z implementation that you do. At the same time, you're running Agents in a scalable, performant, and reliable way with a proven out orchestration/clustering platform.
Example: You want to run 200+ Agents, but only spread across 6-8 k8s Pods. The Agents still perform as well as expected while keeping the underlying infrastructure costs (both resources and actual financial costs) low.
In this session, you will learn about the OSS project that makes this happen - Agent Substrate, with key topics including:
1. Build on top of k8s primitives (clustering of resources for performant sandboxed Agents).
2. Implement a specialized and efficient a Control/Management Plane that's built for the world of agentic.
3. How Substrate Actors running Agents are 90% more efficient (proven in benchmarks) for cost optimization in comparison to Agents in k8s Pods.
4. Efficient and much smaller footprints for running Agents via Actors.
Michael Levan
Building High-Performing Agentic and Kubernetes Environments | AI Architect & Forward Deployed Engineer | AAIF & CNCF Ambassador | 4x Published Author & International Public Speaker
Saddle Brook, New Jersey, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top