About the summit
Building scalable AI systems and high-performance infrastructure.
Who attends
- VP AI Engineering
- Head of ML Platform
- Director of AI Infrastructure
- Principal ML Engineer
- Head of MLOps
- Staff AI Engineer
What the programme covers
- GPU & Compute StrategyCapacity, cost and the hyperscaler vs self-host calculus.
- Inference at ScaleServing, batching, quantisation and serving stacks.
- MLOps & PlatformModel registries, deployment, monitoring at hundreds of models.
- AI ObservabilityTracing, evaluation, drift detection in production.