AI Engineer World's Fair 2024
2024-06-25..2024-06-27
-- online --
[AI Engineer World's Fair 2024, AI Engineer World's Fair 2025, AI Engineer World's Fair 2026]
as the organisers put it
Join 2,000 software engineers enhanced by and building with AI. June 25 - 27, 2024, San Francisco.
who it's for
ai engineers, machine learning engineers, software engineers, platform engineers, data engineers, devops engineers
topics
Llama 3 at 1,000 tok/s; RAG with LangChain; ChromaDB and PGVector vector stores; LoRA fine-tuning via OpenPipe; TensorRT LLM to API endpoints; real-time STT/TTS voice agents; Convex vector database workflows; GitHub Copilot in Codespaces; secure code interpreter sandboxes; Azure AI Studio prompt flow; Knowledge Graphs and GraphRAG (Neo4j); LangGraph and LangSmith testing
| title | author | length |
|---|---|---|
| AI Music Generation, From Prompt to Production | Phlo Young | 55m |
Hands-on demos of Suno and Udio generate short songs, loops and 30‑second stems from prompts and uploaded audio, with a provided Premier login for unlimited… | ||
| Building an AI assistant that makes phone calls | Tom Redman | 51m |
Workshop shows a working voice assistant that makes live phone calls, streams audio to Google Cloud for realtime transcription, routes conversation through… | ||
| LLM Quality Optimization Bootcamp | Thierry Moreau, Pedro Torruella | 53m |
Fine-tunes a Llama 3 8B model on 10,000 examples from the PImasking-200k dataset using OpenPipe, exports a 50MB LoRA and deploys it on OctoAI. Evaluation on… | ||
| Llama 3 at 1,000 tok/s on the SambaNova AI Platform | Varun Badrinath Krishna, Petro Junior Milan | 01h 01m |
Demo shows Llama‑3‑8B‑Instruct at 1,000 tok/s running on SambaNova’s SN40L RDU with a three‑tier memory stack; measured time‑to‑first‑token ~0.19s and… | ||
| Github Copilot - The World's Most Widely Adopted AI Developer Tool | Christina Warren | 01h 20m |
Live demo of GitHub Copilot shows concrete workflows: code completions (ghost text), Copilot Chat and inline chat that generate code, explain functions, write… | ||
| How to add secure code interpreting in your AI app | Vasek Mlejnsky | 01h 48m |
Builds a Next.js chat + preview that runs AI‑generated Python inside per‑user sandboxes using Sonnet 3.5, Vercel AI SDK and E2B Code Interpreter SDK. Claims… | ||
| Build, Evaluate and Deploy a RAG-Based Retail Copilot with Azure AI | Cedric Vidal, David Smith | 01h 58m |
Backend walkthrough that builds a production RAG retail copilot using Azure AI Studio and prompt flow, with code run in GitHub Codespaces and data in Cosmos DB… | ||
| AI Templates | Gabriela, Aishwarya | 01h 03m |
Workshop shows how to run production-ready AI templates from GitHub in minutes using GitHub Codespaces and an Azure OpenAI proxy (so no private-preview… | ||
| Knowledge Graphs & GraphRAG: Techniques for Building Effective GenAI Applications | Zach Blumenthal | 01h 40m |
Workshop shows a working GraphRAG pipeline that combines Neo4j (sandbox) + OpenAI embeddings + LangChain retrievers to reduce hallucination and personalize… | ||
| Build an AI Research Agent | Apoorva Joshi | 28m |
Walks through building a working AI research agent that searches arXiv, returns ranked paper lists, generates concise summaries, and answers follow-up… | ||
| Architecting and Testing Controllable Agents | Lance Martin | 02h 22m |
Shows how to build agents that trade off flexibility for reliability by constraining control flow with LangGraph, then measures both final answers and… | ||
| Building and Scaling an AI Agent Swarm of low latency real time voice bots | Damien Murphy | 01h 07m |
Builds a real-time audio-in/audio-out agent using Deepgram for low‑latency STT/TTS, configurable LLMs (OpenAI GPT‑4o shown), and NodeJS client/server with… | ||
| From model weights to API endpoint with TensorRT LLM | Philip Kiely, Pankaj Gupta | 01h 40m |
TensorRT-LLM is shown as a production-ready toolkit that converts Hugging Face weights into GPU-specific TensorRT engines and runs them via Triton or a custom… | ||
| Build enterprise generative AI apps using Llama 3 at 1,000 tokens/s on the SambaNova AI platform | Varun Badrinath Krishna, Petro Junior Milan | 55m |
Claims a live Llama-3 deployment running Llama-3-8B-Instruct at 1,000 tokens/s on SambaNova hardware (SN40L RDU) and a trillion-parameter CoE (Samba-1); shows… | ||
| Git push get an AI API | Ryan Fox-Tyler | 45m |
Builds a live demo that classifies GitHub issues, summarizes trends, and finds similar items using Hypermode; code compiles AssemblyScript to WebAssembly and… | ||
| 10x Development: LLMs For the working Programmer | Manuel Odendahl | 01h 15m |
Practical workshop showing concrete workflows: transform meeting transcripts into YAML GitHub issues and Slack notifications, generate small helper scripts… | ||
| Building with Anthropic Claude: Prompt Workshop | Zack Witten | 01h 35m |
Hands-on prompt workshop where attendees drop real prompts into the Anthropic console and iterate live, proving concrete fixes: use an assistant prefill (an… | ||
| Running AI Application in Minutes w/ AI Templates | Gabriela de Queiroz, Pamela Fox, Harald Kirschner | 01h 29m |
Claims rapid prototyping that can deploy in minutes using AI templates plus GitHub Codespaces and Azure credits (up to $150,000). Three ready templates are… | ||
| Low Level Technicals of LLMs | Daniel Han | 02h 52m |
Hands-on workshop shows exactly what was fixed and how: debugged Gemma and Phi‑3 implementations (including a rope float32 fix that causes the largest… | ||
| nothing matches | ||