Register
LLM text generation is well-established, but what happens when you need to select optimal choices from thousands of options? How do you architect systems that apply user-defined constraints and business rules reliably? This session covers our journey at Nooxit: architecture patterns for LLM-powered selection and validation strategies that work in production. You'll learn practical approaches to choose from a variety of options that scale beyond simple text generation.
Speaker
Jendrik Jördening
CTO @Nooxit, Developing ML Algorithms & MLOps Infrastructure | Previously @Aurubis and @Akka
Jendrik Jördening is CTO at Nooxit, where he is developing ML algorithms, MLOps infrastructure and managing the internal kubernetes clusters. He formerly worked at Aurubis and Akka Germany on Data Science and Deep Learning in the field of industry 4.0 and autonomous machines.
At the same time he took part in the Udacity Self-Driving Car Nanodegree, participating with a group of other Udacity student with a car in the Self-Racing Cars event at the Thunderhill race-track in California.
