Coding Agents Lunch & Learn Session 9 : End-to-End MLOps with Autonomous Agents

In this session, we’ll explore how coding agents can orchestrate a full MLOps pipeline, from data ingestion to deployed models, without manual intervention.

Leo Walker will walk us through a real project built at the Stanford “LLM x Law” Hackathon, where agents were used to:

Pull and process data from external APIs

Use LLMs for parsing and data cleaning

Train classification and regression models

Deploy model weights to Hugging Face

Expose models via MCP servers for agent-to-agent interaction

We’ll discuss how this approach shifts workflows from manual pipelines to coordinated agent systems, and what that means for the future of MLOps and applied AI.

This session is ideal for anyone interested in:

AI agents in production workflows

Automating ML pipelines

Practical applications of LLMs beyond prompting

Speakers

Leo Walker

AI Engineer @ KaiCare.ai

Demetrios Brinkmann

Chief Happiness Engineer @ MLOps Community

Rahul Parundekar

Founder @ A.I. Hero, inc.

Agenda

4:00 PM

4:05 PM

GMT

Opening / Closing

Welcome & Context

What is Lunch & Learn Why coding agents + MLOps

+ content:video.read_more_button

4:05 PM

4:35 PM

GMT

Presentation

Project Walkthrough & Live System Breakdown

Overview of the hackathon project Architecture of the agent-driven pipeline Tools used (LLMs, APIs, Hugging Face, MCP)Data ingestion → processing → modeling → deployment How agents coordinate across steps Demo of MCP server + model usage

+ content:video.read_more_button

4:35 PM

4:50 PM

GMT

Fireside Chat

Discussion: Agents + MLOps

Benefits vs traditional pipelines Reliability, observability, and control Where this approach breaks

+ content:video.read_more_button

4:50 PM

5:00 PM

GMT

Fireside Chat