AI Engineer World's Fair 202516:41
Effective AI Agents Need Data Flywheels, Not The Next Biggest LLM – Sylendran Arunagiri, NVIDIA
Sylendran Arunagiri
Architecture · Agent engineering · Observability and reliability
← Featured AI Engineer talks
The talk archive.
1,011 published talks.
AI Engineer Code 202520:19
Efficient Reinforcement Learning
Rhythm Garg · Linden Li
Data and model adaptation · Infrastructure and deployment · Observability and reliability
AI Engineer World's Fair 202418:42
Embeddings are Stunting Agents: How Codeium Breaks Through the Ceiling for Retrieval
Kevin Hou
Coding and developer tools · RAG, context, and search · Developer workflows and testing
AI Engineer World's Fair 20245:41
Emergence Launch: AI Agents and the future enterprise
Satya Nitta
Evals · Coding and developer tools · Agent engineering
AI Engineer World's Fair 202616:33
Emulated: The data for fully autonomous software engineers and companies
Joseph Wang · Sid
Data and model adaptation · Developer workflows and testing · Observability and reliability
AI Engineer World's Fair 202616:30
Ending AI Slop
Thais Castello Branco
Observability and reliability · Safety and governance · Enterprise
AI Engineer World's Fair 202524:46
Engineering Better Evals: Scalable LLM Evaluation Pipelines That Work
Dat Ngo · Aman Khan
Evals · RAG, context, and search
AI Engineer Europe 202624:35
Engineering voice agents: Latency, quality, and scale
Rishabh Bhargava
Infrastructure and deployment · Safety and governance · Speech and audio
AI Engineer Summit 202515:28
Ensure AI Agents Work: Evaluation Frameworks for Scaling Success
Aparna Dhinkaran · Aparna Dhinakaran
Architecture · Reasoning and models · Industry applications
AI Engineer World's Fair 202612:08
Enterprise Agents Have a Structure Problem - Ishita Daga, Tesla
Ishita Daga
RAG, context, and search · Safety and governance · Agent engineering
AI Engineer Code 20255:19
Enterprise Deep Research: The Next Killer App for Enterprise AI — Ofer Mendelevitch, Vectara
Ofer Mendelevitch
RAG, context, and search · Leadership · Safety and governance
AI Engineer World's Fair 202623:13
Evaling Video Slop
Maor Bril
Speech and audio · Creative and generative media · Vision and video
AI Engineer World's Fair 202548:31
Evals 101 — Doug Guthrie, Braintrust
Doug Guthrie
Evals · Coding and developer tools · APIs, MCP, and protocols
AI Engineer Europe 202619:04
Evals Are Broken, Use Them Anyway
Ara Khan
Coding and developer tools · Agent engineering
AI Engineer World's Fair 202515:22
Evals Are Not Unit Tests
Ido Pesok
RAG, context, and search · Evals · Infrastructure and deployment
AI Engineer World's Fair 202621:17
Evals Driven-Development: Engineering a Mental Health AI Coach Ethically & Safely
Akele Reed · Dave Revere · Doug Keller
Other / unclassified · Healthcare · RAG, context, and search
AI Engineer World's Fair 20251:25:08
[Evals Workshop] Mastering AI Evaluation: From Playground to Production
Carlos Esteban · Doug
APIs, MCP, and protocols · Evals · Coding and developer tools
AI Engineer World's Fair 202520:33
Evaluating AI Search: A Practical Framework for Augmented AI Systems
Julia Neagu · Deanna Emery · Maitar Asher
Safety and governance · Evals · RAG, context, and search
AI Engineer World's Fair 202514:40
Events are the Wrong Abstraction for Your AI Agents
Mason Egger
Architecture · APIs, MCP, and protocols · Infrastructure and deployment
AI Engineer World's Fair 202621:08
Every company should have a Brain — Garry Tan, Y Combinator
Garry Tan
Leadership · Reasoning and models · RAG, context, and search
AI Engineer World's Fair 202615:36
Every Harness Will Become A Claw
Sam Bhagwat
Safety and governance · Agent engineering · RAG, context, and search
AI Engineer World's Fair 202610:51
Every Solo Agent Builder Eventually Reinvents a Worse Version of CI/CD
Sumaiya Shrabony
Coding and developer tools · Evals · Architecture
AI Engineer Europe 202620:13
Everything I Learned Training Frontier Small Models
Maxime Labonne
Infrastructure and deployment · Reasoning and models · RAG, context, and search
AI Engineer World's Fair 202621:11
Everything Is a Rollout — Alex Shaw + Ryan Marten, Terminal-Bench, Harbor, Laude Institute
Alex Shaw · Ryan Marten
Evals · Coding and developer tools · Safety and governance
AI Engineer World's Fair 202525:15
Everything is ugly, so go build something that isn't
Raiza Martin
Enterprise · Other / unclassified
AI Engineer World's Fair 202616:02
Everything we knew about software has changed — Theo Browne
Theo Browne
Infrastructure and deployment · Coding and developer tools · Developer workflows and testing
AI Engineer Europe 202650:25
Everything You Need To Know About Agent Observability
Danny Gollapalli · Ben Hylak · Zubin Koticha
Observability and reliability · Coding and developer tools · Other / unclassified
AI Engineer World's Fair 202417:52
Everything you need to know about Finetuning and Merging LLMs
Maxime Labonne
Data and model adaptation · Evals · Reasoning and models
AI Engineer Code 202513:25
Evolving Claude APIs for Agents
Katelyn Lesse
APIs, MCP, and protocols · RAG, context, and search · Developer workflows and testing
AI Engineer World's Fair 202518:05
Exposing Agents as MCP Servers with mcp-agent: Sarmad Qadri
Sarmad Qadri
Architecture · Agent engineering · APIs, MCP, and protocols
AI Engineer World's Fair 20246:13
EyeLevel Launch: Your RAG is Tripping, Here's the Real Reason Why
Benjamin Fletcher
Coding and developer tools · RAG, context, and search
AI Engineer Europe 202618:02
Fast Models Need Slow Developers
Sarah Chieng
RAG, context, and search · Infrastructure and deployment · Coding and developer tools
AI Engineer Europe 202610:11
Feedback Loops are All You Need
Mehedi Hassan
Architecture · Speech and audio · Observability and reliability
AI Engineer World's Fair 202621:32
fighting slop with slop
Vaibhav Gupta
Evals · Speech and audio · Architecture
AI Engineer World's Fair 202620:24
First Steps Toward Automated AI Research
Richard Socher
RAG, context, and search · Evals · Other / unclassified
AI Engineer World's Fair 202519:46
Five Hard-Earned Lessons About Evals
Ankur Goyal
Data and model adaptation · Evals · RAG, context, and search