AI Performance Testing: How to Scale Agentic AI with Kandasamy Selvaraj

About This Episode:

Everything you knew about performance testing changes when the system you’re testing is non deterministic.

In this episode of the TestGuild Automation Podcast, Joe Colantonio sits down with Kandasamy Selvaraj, Principal Architect and author of the free book Rethinking Performance Engineering for Agentic AI, to unpack what it really takes to move an AI agent from a working demo to an enterprise system handling millions of conversations per hour.

Checkout his free book: https://leanpub.com/agentic-ai-performance

Kandasamy shares the practical playbook he’s built running agentic AI in production, including why the same request can take three seconds one run and eight seconds the next, how to use harnesses to bound tool calls, reasoning loops, and token budgets, and why your SRE dashboard can look perfectly healthy while your token costs quietly balloon to five times baseline.

You’ll learn how his team:

• Shifts performance gates left into every commit with JMeter
• Shifts right with synthetic monitors on blue green deployments
• Uses Langfuse and OpenTelemetry to spot context bloat before it hits production.

You’ll also hear how to:

• Slash AI costs with prompt caching
• Conversation capping
• Routing simple queries to cheaper models
• Why you should load test at the API layer before touching the UI,
• How to keep stubs honest with production sampled latency
• Why one misbehaving agent can starve every other agent sharing the same provider.

If you’re a tester, performance engineer, SRE, or architect building on LLMs, this conversation will change how you think about scale.

0:00 / 0:00

Join the Guild for (FREE)!

Email New Tab

About Kandasamy Selvaraj

Kandasamy Selvaraj is a Performance Engineering Leader, Principal Architect, and Performance Evangelist with 19+ years of experience in cloud-native platform engineering, specializing in the performance, reliability, and scalability of distributed systems that sustain millions of transactions at scale. He currently leads performance engineering and observability initiatives safeguarding next-generation enterprise platforms and agentic AI systems. He recently authored Agentic AI Performance Engineering, a practical, hands-on guide for Product Leaders, Architects, SRE Engineers, DevOps Teams, and Performance Engineers building production-ready agent fleets. The book is available at leanpub.com/agentic-ai-performance.

Kandasamy has built a distinguished career translating performance insight into measurable business outcomes. He championed shift-left performance practices and automated performance gates in CI/CD pipelines, reducing production defects by 80% and accelerating deployments by 40%.

His multi-tier optimization work, spanning JVM tuning, database optimization, async messaging, and infrastructure right-sizing,delivered 75% latency reductions while supporting millions of concurrent users. Among his standout achievements is a cluster-enabled caching framework that achieved 85% cache-hit rates and drove 50x throughput gains. He has led multiple large-scale performance initiatives, including engineering Super Bowl–scale event infrastructure from the ground up,stress-testing systems to 10x target throughput and validating resilience for over one million concurrent users, all with zero downtime on game day.

He also conducted real-time, in-flight performance engineering for GOGO Wi-Fi across U.S. commercial airlines, running production load tests above 10,000 feet to tune ATG signal performance (forward and reverse ATG links) and ensure scalable wireless delivery in the air. His broader portfolio spans high-impact performance and scalability engineering across insurance, retail, financial services, healthcare, and airline connectivity industries.

A strong advocate for observability, Kandasamy implemented enterprise APM tooling using a monitoring-as-code approach and deployed chaos engineering practices that achieved 99.99% platform availability. He holds an AWS Certified Solutions Architect credential, a Certified Chaos Engineering Practitioner certification, an APM Associate Certification, a Generative AI Certified Professional credential, and a Post Graduate Program in Artificial Intelligence and Machine Learning.

Connect with Kandasamy Selvaraj

• • LinkedIn: www.kandasamy-selvaraj-3ab97835/

Rate and Review TestGuild

Thanks again for listening to the show. If it has helped you in any way, shape, or form, please share it using the social media buttons you see on the page. Additionally, reviews for the podcast on iTunes are extremely helpful and greatly appreciated! They do matter in the rankings of the show and I read each and every one of them.