his session explores how Canva leverages Karpenter to scale and optimize diverse workloads on Amazon EKS. Learn how Canva manages AI workloads using On-Demand Capacity Reservations (ODCRs) and EC2 Capacity Blocks for ML, while maximizing resource utilization by intelligently co-locating CPU and GPU workloads on GPU nodes. We will dive into NodePool management strategies for efficient scheduling of AI workloads and examine how Canva uses a range of Amazon EC2 instance types to operate a multi-tenant container orchestration platform for all workloads, optimizing for cost-effectiveness and resource efficiency. Ideal for platform engineers and Kubernetes operators looking to optimize their EKS clusters for both AI and general workloads at scale.
What this session is about
Playbook
Editorial commentary · what to actually do about this on Monday
Independent editorial perspective — not an official AWS or speaker statement. Designed for executives evaluating what to brief their teams on next.
Live updates related to this session LIVE
Sourced via Parallel AI Monitor — continuous web watch on 21 topical streams. Updated .
- redis.io high confidence Scaling infra for agent workloads
Upcoming events & webinars - Redis
Qovery published a technical guide on June 19, 2026, detailing the best tools for integrating and running AI agent workloads on Kubernetes. The guide emphasizes that agent-native workloads are highly stateful and require specialized infrastructure for GPU scheduling and orchestra
- qovery.com high confidence Scaling infra for agent workloads
The Best Tools for Integrating AI Agents with Kubernetes in ...
Qovery published a technical guide on June 19, 2026, detailing the best tools for integrating and running AI agent workloads on Kubernetes. The guide emphasizes that agent-native workloads are highly stateful and require specialized infrastructure for GPU scheduling and orchestra
- agentbrisk.com high confidence Scaling infra for agent workloads
AI Agent Rate Limiting: Anthropic, OpenAI, Google Limits and ...
Qovery published a technical guide on June 19, 2026, detailing the best tools for integrating and running AI agent workloads on Kubernetes. The guide emphasizes that agent-native workloads are highly stateful and require specialized infrastructure for GPU scheduling and orchestra
- zylos.ai high confidence Scaling infra for agent workloads
Rate Limiting and Backpressure Patterns for AI Agent APIs
CallSphere published a detailed architectural guide on scaling AI agents to 10,000 concurrent users, outlining the use of a Gateway Layer, stateless Agent Worker Pools with Redis session state, and LLM Connection Pools with async semaphores to manage API load and concurrency.
- adenhq.com high confidence Scaling infra for agent workloads
The Native Cloud for AI Agents - Aden
Fast.io published a comprehensive 2026 guide on AI Agent Retry Patterns, detailing the implementation of exponential backoff with jitter to prevent 'retry storms' (backpressure) and the use of circuit breaker patterns to protect agents from cascading failures. The guide provides
External links matched to this session via topic relevance. The KB does not endorse third-party content; verify before citing.