Kubernetes Bin-Packing & Production Guardrails for LLM Apps

🚀 Join us at Station Austin for Food, Drinks, and Kubernetes on September 24, 2026!

RSVP only here (CNCF official site): [https://ocgroups.dev/cncf/group/3up7rjk/event/w8dw5pt](https://ocgroups.dev/cncf/group/3up7rjk/event/w8dw5pt)

Station Austin (formerly Capital Factory) is generously hosting the Kubernetes Austin meetup! Everyone is welcome whether you are new to Kubernetes or already experienced, come connect with the Austin cloud native community. We'll share the latest updates, practical insights, and real world learnings from Kubernetes, CNCF projects, and modern platform engineering.

FEATURED TALKS

🎤 Steve Fraser — The Bin-Packing Problem Nobody Talks About: What Actually Limits Pod Density in Kubernetes Kubernetes bin-packing looks like a math problem: fit requests into node capacity, let the scheduler handle it. In practice, clusters rarely hit the density that math promises — and the real reasons have little to do with the scheduler itself. This talk walks through the actual limiting factors that cap pod density, using real (anonymized) cluster data: kubelet's --max-pods default and cloud IP allocation limits; the gap between what pods request and what they really consume; topology spread and anti-affinity as a tax on density; CSI volume-per-node limits and IP/NIC exhaustion; and hidden overhead from DaemonSets and reserved resources.

🎤 Shiva Kalyan Reddy Giri & Nitin Garg — From AI Prototype to Kubernetes: Production Guardrails for LLM Applications AI applications can move from idea to working prototype quickly, but deploying them reliably introduces challenges that model demonstrations often hide. This session presents a cloud-native architecture for moving an API-driven generative AI application toward Kubernetes, covering autoscaling, secrets management, health checks, resource controls, rolling deployments, workload isolation, and failure recovery — plus scaling stateful WebSocket sessions, managing external model rate limits, tracing requests across AI services, and designing graceful degradation. The talk is vendor-neutral.

AGENDA 6:30 PM – 7:00 PM — The Bin-Packing Problem Nobody Talks About (Steve Fraser) 7:15 PM – 7:45 PM — From AI Prototype to Kubernetes (Shiva Kalyan Reddy Giri & Nitin Garg)

📍 VENUE Station Austin — Apollo Room, 1st Floor 701 Brazos St, Austin, TX 78701 Upon arrival at the building, please proceed to the 1st floor, Apollo room. We'll be in the Apollo Room, 1st Floor (look for Capital Factory signs) after 5:45 pm.

PARKING We know parking in Downtown is tricky! So, you can park in the building garage for just $8.00 (validation parking tickets will be distributed)! Street parking will still be an option. More information on parking here: [https://www.capitalfactory.com/parking/](https://www.capitalfactory.com/parking/)

🏢 VENUE SPONSORED BY STATION AUSTIN Thank you to Station Austin for sponsoring Kubernetes Austin! Station Austin is the center of gravity for entrepreneurs in Texas. They meet the best entrepreneurs in Texas and introduce them to their first investors, employees, mentors, and customers. To sign up for a Station Austin membership: [https://stationaustin.org/commons/](https://stationaustin.org/commons/)

🤖 SPONSORED BY CAST AI Thank you to Cast AI for sponsoring Kubernetes Austin! Cast AI is the Kubernetes automation platform that keeps application performance and cloud costs on autopilot. It continuously analyzes how workloads actually behave and automatically tunes CPU, memory, and infrastructure provisioning. Learn more at [https://cast.ai/](https://cast.ai/)

Full event details and RSVP only here (CNCF official site): [https://ocgroups.dev/cncf/group/3up7rjk/event/w8dw5pt](https://ocgroups.dev/cncf/group/3up7rjk/event/w8dw5pt)

Looking forward to seeing you there!