Deploy AI in 5 Minutes: A Hands-On Inference Challenge

​DigitalOcean's Serverless Inference lets you deploy AI models with a single API call — OpenAI-compatible, auto-scaling, pay-per-token.

​In this hands-on masterclass:

• ​See a live side-by-side model comparison in the Model Playground

• ​Watch a Serverless Inference endpoint go from zero to live in under 5 minutes

• ​Compete in a Prompt Battle using just your phone

• ​Race to deploy your own endpoint

​Whether you're evaluating inference providers, building your first AI feature, or optimizing an existing stack, you'll leave with a working endpoint and the knowledge to scale it.

​Speaker:

​Jeff Fan, Senior Solutions Architect, DigitalOcean -

​Jeff Fan is a Senior Solutions Architect at DigitalOcean, where he designs and optimizes Kubernetes-based GPU infrastructure for generative AI workloads, specializing in LLM inference and cost-efficient scaling. Prior to DigitalOcean, he built and operated mission-critical systems for leading German enterprises. Jeff is known for translating complex cloud and AI concepts into clear, actionable guidance - publishing articles that turn technical challenges into straightforward, actionable steps for engineering teams.