End-to-end stack for building custom LLMs
In this webinar, we’ll walk through a modern stack for developing domain-specific LLMs using the latest post-training techniques — including custom reward functions, as popularized by Deepseek.
These cutting-edge methods are now within reach for any company, thanks to cost-efficient infrastructure from Nebius and a user-friendly software stack powered by Metaflow.
We’ll also showcase how the new Nebius — Outerbounds integration streamlines the end-to-end workflow for real-world production environments.
What you will know?
-
An introduction to sophisticated post-training, leading to reasoning models
-
Developing such custom LLMs in a production-grade environment
-
The components of an end-to-end stack for custom LLMs — what are they and why they matter
For who?
ML/AI engineers, Data Scientists, Research engineers, Platform engineers.
When?
May 20, Tuesday.
19:00 CEST (UTC +2) / 10:00 PDT (UTC –7)