AWS Builder Center

Builder Center

Own Your AI: Build an Agentic AI Model Factory on AWS - Hackathon

Build an ML Engineer Agent that evaluates, fine-tunes, deploys, and improves open models, running entirely in your own AWS account. Bring a laptop. Leave with a factory.

Join the AWS Builder Loft Spaces: https://builder.aws.com/connect/space/5c1e07ec-3701-36b1-abd2-16fcc221b82f/aws-builder-loft-san-francisco-usa-community-and-events 

Event Overview

Build a Sovereign AI Model Factory: an ML Engineer Agent that evaluates, fine-tunes, deploys, and improves open models using Union on your cloud.
The best AI teams aren't renting every capability from an external API, they're building systems they own and control. In this hands-on session at the AWS Loft, we'll build exactly that.
We'll start with a walkthrough where we build a LangGraph-powered agent that evaluates open models in parallel, fine-tunes promising candidates, deploys the winner, and retrains automatically when performance drops. Think of it as the first brick in your own model factory: a repeatable system for evaluating, improving, and deploying models you control, not a black box you call and hope for the best.
Along the way, you'll see how Union.ai gives your workflows a durable runtime with infrastructure as context, so agents adapt infra resources, recover from failures, and keep moving without re-running completed work. And because it all runs in your own AWS account, you own the full stack end to end: your models, your data, your infrastructure, your IP.
Then we switch into build night mode: keep building on the example, bring your own models or datasets, experiment with evals and fine-tuning, extend open models to different parts of your agent, or start something new around the same ideas.
Bring a laptop. Leave with a factory.

Event Details

Agenda

  • 5:00 – 5:25 PM: Registration, dinner, and networking
  • 5:25 – 5:35 PM: Welcome and introduction (Union.ai)
  • 5:35 – 5:55 PM: Building a Sovereign AI Model Factory on AWS: durable runtime, infrastructure as context, and owning your stack
  • 5:55 – 6:20 PM: Guided build: a LangGraph agent that evaluates open models in parallel, fine-tunes candidates, deploys the winner, and retrains when performance drops
  • 6:20 – 7:20 PM: Build session: extend the example or bring your own models and datasets, with mentors on hand
  • 7:20 – 7:45 PM: Participant demos (optional)
  • 7:45 – 8:00 PM: Closing and next steps

What You'll Learn - By the end, you will be able to:

  • Build an agent that evaluates and compares open models in parallel
  • Fine-tune promising candidates and deploy the best-performing model
  • Set up automatic retraining when model performance drops
  • Use a durable runtime that adapts infrastructure and recovers from failures without re-running completed work
  • Run the full stack (models, data, infrastructure) in your own AWS account

Who Should Attend - This event is designed for:

  • ML and AI engineers building or fine-tuning models on open weights
  • Developers building agents with LangGraph or similar frameworks
  • Platform and MLOps engineers running AI workloads on AWS
  • Teams thinking about sovereign AI and owning more of their stack

Prerequisites - To get the most out of this session:

  • You should be comfortable with Python; familiarity with LLMs or agents is helpful
  • Bring a laptop
  • Optional: bring your own model or dataset to experiment with

Why This Event Matters

For teams thinking about sovereign AI, this is a practical starting point for owning more of your stack: the weights, the training loop, the evals, and the infrastructure it runs on, all on AWS.
Hosted by Sage Elliott, Developer Advocate at Union.ai, with the Union.ai team.

Final Notes! - Spots are limited. Register now to secure your spot!

Here is the registration link again: https://events.builder.aws.com/EAlGMy
See you at the Loft! We're at 525 Market St, 2nd Floor, San Francisco. You'll need a valid government-issued physical photo ID (digital IDs are not accepted) and must be 18+ to enter. Bikes and scooters are not allowed in the building, and there is no on-site parking.
# builder-loft# builder-loft-SF# loft-events# ai-agents# generative-ai
Any opinions in this article are those of the individual author and may not reflect the opinions of AWS.
Enjoyed reading this content? Let the author know!

Your likes, comments, shares, and saves help creators reach more builders.

Loading recommendations

Loading article