Engineering posts about Kubernetes
Curated summaries and key learnings for engineers working with Kubernetes.
DigitalOcean Dedicated Inference: A Technical Deep Dive
The article delves into DigitalOcean's Dedicated Inference service, designed to efficiently manage large language model (LLM) inference at scale. It highlights the challenges of handling high...
Finding zombies in our systems: A real-world story of CPU bottlenecks
The article narrates a real-world investigation by the Kubernetes platform team at Pinterest into CPU bottlenecks affecting their Ray-based machine learning training jobs. The team faced intermittent...
Welcome to Agents Week
The article introduces 'Agents Week' at Cloudflare, highlighting the shift in cloud infrastructure to accommodate AI agents, which operate on a one-to-one basis rather than the traditional...
NVIDIA GTC 2026 Confirmed It: The Inference Era Is Here
The article highlights the transition from the training era of AI to the production inference era, emphasizing the importance of operational infrastructure in running AI at scale. It discusses the...
Technical Deep Dive: How DigitalOcean and AMD Delivered a 2x Production Inference Performance Increase for Character.ai
This article presents a comprehensive technical deep dive into the collaboration between DigitalOcean and AMD to enhance the performance of Character.ai's AI models. By optimizing the use of AMD...
Leveling Up Kubernetes: Key DigitalOcean Managed Kubernetes Releases in 2025
The article outlines significant updates to DigitalOcean Managed Kubernetes (DOKS) throughout 2025, emphasizing enhancements in scalability, security, and operational efficiency. Key upgrades include...