Best AI Engineering Videos
Curated talks, tutorials, and deep dives on LLMs, RAG, agents, and production ML.
160 curated videos across 5 categories
AEAI Engineer70 videos
NewBuilding Turbopuffer: Gergely Orosz (@pragmaticengineer ) × Simon Eskildsen (CEO)
TodayWatch on YouTube
Videos
Building Turbopuffer: Gergely Orosz (@pragmaticengineer ) × Simon Eskildsen (CEO)
Today
MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef
Yesterday
MCP Tasks (async): Why Aren't Any Agents Supporting Them? — Cornelia Davis, Temporal
Yesterday
When Will The Benchmaxxing Plague End? — Nick Heiner, Surge AI
Yesterday
Emulated: The Data for Fully Autonomous Software Engineers and Companies — Joseph Wang
3 days ago
Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It — Olive Song
4 days ago
Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google
Jul 25, 2026
From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AI
Jul 25, 2026
Building Closed-Loop Evals for a Multimodal Agent at Scale — Soumya Gupta & Jai Chopra, Uber
Jul 24, 2026
How Evals and Prompts Shape Agent Behavior — Preetika Bhateja & Daniel Bump, YouTube Ads
Jul 24, 2026
From Signal to PR: Anatomy of a Self-Improving Agent — Jason Lopatecki, Arize
Jul 24, 2026
The Future of Evals: From LLM as a Judge to Agent as a Judge — Aparna Dhinakaran, Arize AI
Jul 24, 2026
Vending-Bench: Long-Horizon Agent Evals — Lukas Petersson, Andon Labs
Jul 24, 2026
Perception Agents — Antje Barth, Amazon AGI Lab
Jul 23, 2026
Autonomous Agents for Scientific Tasks - Sina Shahandeh, Radicait
Jul 18, 2026
Agents Need Receipts, Not More Tool Calls - Armanas Povilionis, Alithea Bio
Jul 18, 2026
Agents Need Feature Flags - Sachin Gupta
Jul 18, 2026
Your Agents Need a Save Button - Hamza Tahir, ZenML
Jul 18, 2026
The Great Loops Debate — Dex Horthy, Geoff Huntley, Ian Livingstone, Greg Pstrucha, @insecure-agents
Jul 17, 2026
An AI Agent Became the #1 Contributor in OpenAI's Hiring Challenge — Zhengyao Jiang, Weco
Jul 16, 2026
Computer-Use 2.0: Agents Just Got Multi-Cursor — Francesco Bonacci, Cua
Jul 15, 2026
WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar
Jul 14, 2026
Stop AI Agent Hallucinations: 5 Techniques + Production Patterns - Elizabeth Fuentes, AWS
Jul 11, 2026
The Factory That Dreams: 39 AI Agents, No Framework - Rushabh Doshi, Machinecraft
Jul 11, 2026
Every Solo Agent Builder Eventually Reinvents a Worse Version of CI/CD - Sumaiya Shrabony
Jul 11, 2026
Special Topics in Kernels, RL, Reward Hacking in Agents — Daniel Han, Unsloth
Jul 11, 2026
Design Patterns for AI Trust: Juries, Libraries, and Agent Tiers — Alex Bauer, Upside.tech
Jul 11, 2026
Teaching AI to Find Real Vulnerabilities — David Brumley, Bugcrowd
3 days ago
Rethinking Environments for Long-Horizon Work — Rayan Garg, Theta Software
3 days ago
What's Next After RLHF? — Diogo Almeida, TypeSafe AI
3 days ago
Data Quality Is the Compute Multiplier — Ari Morcos, DatologyAI
3 days ago
Learning on the Job: The Future of Post-Training — Raymond Feng, Applied Compute
3 days ago
Data and Environment Curation for Post-Training LLMs — Mahesh Sathiamoorthy, Bespoke Labs
3 days ago
The Base Model Is Dead — Varun Singh, Arcee AI
3 days ago
Verifiable Environments for AI in Biology — Kenny Workman, LatchBio
3 days ago
Ending AI Slop — Thais Castello Branco, Taste Labs
3 days ago
Benchmarks: The Good, the Bad, and the Ugly — Ali Khial, G2i
3 days ago
Reinforcement Learning without Verifiable Rewards — Will Brown, Prime Intellect
3 days ago
fighting slop with slop — Vaibhav Gupta, Boundary
4 days ago
DeepSWE: A Contamination-Resistant Coding Benchmark — James Shi, Datacurve
Jul 26, 2026
State of Data — Sean Cai, Independent / State of Data
Jul 26, 2026
The Messy Reality of Scale: Synthetic Data and Pre-Training — Marah Abdin & Robert McHardy, poolside
Jul 26, 2026
Evals-Driven Development for a Mental Health AI Coach — Akele Reed & Dave Revere, SonderMind
Jul 25, 2026
Loop Engineering from First Principles — Kyle Mistele, HumanLayer
Jul 25, 2026
Evaling Video Slop — Maor Bril, Character.ai
Jul 25, 2026
Everything Is a Rollout — Alex Shaw + Ryan Marten, Terminal-Bench, Harbor, Laude Institute
Jul 24, 2026
Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex
Jul 24, 2026
Training Frontier Models to Out-Think Hackers — Uri Rolls, Arithmetic & Thom Wolf, Hugging Face
Jul 24, 2026
The Unreasonable Effectiveness of Separating the Task from the Model — Maxime Rivest & Isaac Miller
Jul 23, 2026
Notion's Token Town — Sarah Sachs, Notion
Jul 23, 2026
Harness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayer
Jul 23, 2026
AI on Your Lakehouse: Context Comes in Shapes, Not Queries — Zach Blumenfeld, Neo4j
Jul 23, 2026
Road to 5 Million Tokens: Breaking Barriers in Long Context Training — Max Ryabinin, Together AI
Jun 8, 2026
Benchmarking semantic code retrieval on Claude Code — Kuba Rogut, Turbopuffer
Jun 3, 2026
Connecting the Dots with Context Graphs — Stephen Chin, Neo4j
May 16, 2026
Combine Skills and MCP to Close the Context Gap — Pedro Rodrigues, Supabase
May 15, 2026
Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked
May 3, 2026
Context Is the New Code — Patrick Debois, Tessl
May 3, 2026
MCP = Mega Context Problem - Matt Carey
Apr 25, 2026
Jack Morris: Stuffing Context is not Memory, Updating Weights is
Dec 29, 2025
Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoning
3 days ago
Forward Deployed Engineering at Cursor — Pauline Brunet
Jul 14, 2026
GPU Cloud Deployment Without Leaving Your IDE — Audry Hsu, RunPod
Jun 9, 2026
Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod
Jun 7, 2026
Task Fidelity Scaling Laws — Kobie Crawdord, Snorkel
Jun 2, 2026
Lessons from Trillion Token Deployments at Fortune 500s — Alessandro Cappelli, Adaptive ML
May 12, 2026
Build & deploy AI-powered apps — Paige Bailey, Google DeepMind
Apr 29, 2026
Lessons from Scaling GitHub's Remote MCP Server — Sam Morrow, GitHub
Apr 27, 2026
What we learned scaling MCPs to Enterprise — Karan Sampath, Anthropic
Apr 27, 2026
VoiceOps-fying Low-Latency Intelligence Extraction from Messy Audio Streams — Dippu Kumar Singh
Apr 8, 2026
LALangChain31 videos
Videos
Building Deep Agents and Deploying in Production
3 days ago
Why Do AI Agents Hallucinate?
3 days ago
The misaligned incentives behind AI coding agents
4 days ago
Deep Agents in 1 sentence
5 days ago
Autonomous Agent Improvement with LangSmith Engine | New LangChain Academy Course
5 days ago
How Credit Genie Debugs Thousands of Agent Traces with LangSmith
Jul 27, 2026
Inside the Agent Engine: A LangChain and Traversal Fireside Chat
Jul 24, 2026
The Art of Loop Engineering: How to Build Agents That Improve Over Time
Jul 23, 2026
Build a secure computer for your agent
Jul 23, 2026
How Salesforce Standardizes Agent Evals with LangSmith
Jul 23, 2026
The Agent Development Lifecycle 101 by Harrison Chase
Jul 22, 2026
60% Faster Time-to-Interview: Transforming Hiring with AI Agents with LangChain
Jul 22, 2026
Trace Every Cursor Agent Turn in LangSmith
Jul 21, 2026
Interrupt 26: The Agent Conference by LangChain
Jul 21, 2026
LangSmith Sandboxes: A Secure Computer for Your Agent
Jul 20, 2026
How Coinbase Builds Developer Support Agents | Interrupt 26
Jul 20, 2026
Deep Agents Explained
Jul 17, 2026
LangSmith: The Agent Engineering Platform
Jul 17, 2026
What Is an AI Agent, Actually?
Jul 17, 2026
The best AI agents need more humans than you think
Jul 16, 2026
How 11x Built a Slack-Native Bug Triage Agent with LangSmith Fleet
Jul 15, 2026
Inside Toyota's Production System for Agents | Interrupt 26
Jul 15, 2026
The LangChain Team Answers the Most Searched Questions About Agents
Jul 14, 2026
Not Every Bug Engine Finds Is Worth Fixing
Jul 27, 2026
What Is RAG, Actually?
Jul 24, 2026
How Bridgewater Built Pat, The AI Pocket Analyst Tool | Interrupt 26
Jul 24, 2026
Why Sierra bets on outcome-based pricing #Shorts
Jul 23, 2026
How to manage context the right way with LangSmith's Context Hub
May 27, 2026
Hot vs. cold context isn't about time — it's about whether it's being used | Max Agency #podcast
May 26, 2026
LangChain Academy New Course: Introduction to LangSmith Deployment
May 28, 2026
Make Your LangSmith Deployment Multi-Tenant
Apr 14, 2026
AKAndrej Karpathy15 videos
Videos
How I use LLMs
Feb 27, 2025
Deep Dive into LLMs like ChatGPT
Feb 5, 2025
Let's reproduce GPT-2 (124M)
Jun 9, 2024
Let's build the GPT Tokenizer
Feb 20, 2024
[1hr Talk] Intro to Large Language Models
Nov 23, 2023
Let's build GPT: from scratch, in code, spelled out.
Jan 17, 2023
Building makemore Part 5: Building a WaveNet
Nov 21, 2022
Building makemore Part 4: Becoming a Backprop Ninja
Oct 11, 2022
Building makemore Part 3: Activations & Gradients, BatchNorm
Oct 4, 2022
Building makemore Part 2: MLP
Sep 12, 2022
The spelled-out intro to language modeling: building makemore
Sep 7, 2022
Stable diffusion dreams of psychedelic faces
Aug 19, 2022
Stable diffusion dreams of steampunk brains
Aug 17, 2022
Stable diffusion dreams of tattoos
Aug 16, 2022
The spelled-out intro to neural networks and backpropagation: building micrograd
Aug 16, 2022
DEDeepLearningAI10 videos
Videos
AI writes your code. Who reviews it?
5 days ago
Semantic Search Starts With Embeddings
May 22, 2026
Data is hungry for context
May 14, 2026
A new course on Retrieval Augmented Generation (RAG) is live!
Jan 8, 2026
Learn to implement multi-vector retrieval for image data in this new course
Dec 10, 2025
Fast inference changes what you can build
Jul 15, 2026
Optimize, deploy, and benchmark an open-source LLM with vLLM
Jun 3, 2026
Just deployed to production… and leaked all the credit cards 😬
May 5, 2026
TensorFlow: Data and Deployment Specialization
Feb 25, 2026
AI Dev 25 x NYC | Scott Hurrey: Scaling Enterprise AI with MCP and A2A
Dec 5, 2025
1E100x Engineers8 videos
NewWhy a robot tying a trash bag is bigger than a robot doing a backflip ft. GOOGLE ROBOTICS 2
YesterdayWatch on YouTube
Videos
Why a robot tying a trash bag is bigger than a robot doing a backflip ft. GOOGLE ROBOTICS 2
Yesterday
The ONLY Claude Skills Tutorial Beginners Need in 2026
2 days ago
How To Teach Claude a Workflow Once. It Runs It for Life.
5 days ago
China Built the World's Largest Fusion Magnet — And It's Coming for AI's Energy Problem
6 days ago
Anthropic's Opus 5 just beat every AI model at real coding (and costs less)
Jul 25, 2026
OpenAI built a plugin that lets Codex review your Claude Code
Jul 23, 2026
Anthropic, Blackstone & Goldman Just Built a $1.5B AI Deployment Company
Jul 18, 2026
Roadmap on how to become a Forward Deployed Engineer
May 26, 2026
BMBernard Marr7 videos
Videos
Why Leaders Must Redesign Jobs for the AI Age
3 days ago
What Is Vibe Coding?
4 days ago
What Is AI Psychosis?
5 days ago
Is AI Too Nice to Tell You the Truth? The Hidden Problem of AI Sycophancy
Jul 27, 2026
Inside Future Lab: Exploring Tomorrow's Technology & Innovation
Jul 24, 2026
The Incredible Robots of Goodwood Festival of Speed 2026
Jul 23, 2026
Why Context Is The Missing Piece In Enterprise AI
Jul 2, 2026
THTina Huang6 videos
Videos
My AI COO
Yesterday
AI Agents Explained
Jul 27, 2026
Hermes Agent Fundamentals In 29 Minutes
Jul 20, 2026
Levels of AI Builders
3 days ago
Learn 10X Faster In 10 Minutes
Jul 26, 2026
Tokens Explained
Jul 22, 2026
AAAll About AI2 videos
Videos
How My AI Agent Found a 993% Return Polymarket Strategy
Jul 24, 2026
Opus 5 vs GPT-5.6 On Polymarket Predictions — Week 1
5 days ago
MPMatt Palmer2 videos
Videos
Cap Claude's Context with one environment variable
Jul 6, 2026
AI is all about context
Jan 1, 2026
AEAI Explained1 video
Videos
GPT-6 Goes Rogue? The HuggingFace Incident, Sans Hype
Jul 22, 2026