Evolutionizing Data Pipelines and Personalized AI - MLOps Community
Join us at SPC for an evening of impactful talks and networking at the next NYC MLOps Community meetup.
Talk 1: Building Hyper-Personalized LLM Applications with Rich Contextual DataI
Ajeya Rengarajan, Software Engineer at Tecton, will introduce full Retrieval-Augmented Generation (RAG) and its potential to transform user experiences. We’ll cover four levels of context personalization, from basic recommendations to real-time interactions, showing how richer context—batch, streaming, and real-time inputs—boosts AI performance. We’ll also address the challenges of implementing scalable context solutions and present Tecton’s Context Platform as a way to simplify building and managing personalized data. Using travel recommendations as an example, we’ll demonstrate how developers can easily integrate batch, streaming, and real-time context with simple Python code for more engaging AI experiences.
Talk 2: If You Can’t Reproduce It, It Never Happened.
Crio Greco, Founder & CEO of Bauplan will talk about how ML engineers need reproducible data workloads for development, testing, and debugging. However, code, data, and runtime are often entangled, complicating the process. This talk will cover how to decouple these elements and implement time-travel and branching in data lakes with simple CLI commands for more efficient pipelines.
Networking:
Join us afterward for refreshments and networking.
Location: South Park Commons
Time: 6:00 PM - 9:00 PM
Come to learn, share, and connect with NYC MLOps community!