AI Engineer

Read transcripts, summaries, and section insights from AI Engineer.

📺AI Engineer ·

The Dark Arts of Skill Engineering — Paul Bakaus, Renaissance Geek (Impeccable)

1h 4m · 3h ago
📺AI Engineer ·

Speech-to-Speech Model Research at Google DeepMind — Valeria Wu Fon & Tom Ouyang, Google DeepMind

16m · 1d ago
📺AI Engineer ·

Large clusters for small models — Daniel Svonava, Superlinked

24m · 1d ago
📺AI Engineer ·

Why Software Factories Fail

19m · 1d ago
📺AI Engineer ·

What's New in Inference Engineering — Philip Kiely, Baseten

19m · 2d ago
📺AI Engineer ·

Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli

17m · 2d ago
📺AI Engineer ·

Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads — Sitanshu Gupta, CoreWeave

15m · 2d ago
📺AI Engineer ·

Routing LLM Inference in Production: From Engine Signals to Policy — Qianru Lao & Lu Zhang, OpenAI

17m · 2d ago
📺AI Engineer ·

Operating Distributed Inference Systems at Scale — Nishant Gupta & Naman Ahuja, Meta

19m · 2d ago
📺AI Engineer ·

Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story — Asaf Gardin & Yuval Belfer

17m · 2d ago
📺AI Engineer ·

Are LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google

16m · 2d ago
📺AI Engineer ·

The Frontier AI Inference Cloud for Agents — Byung-Gon (Gon) Chun, FriendliAI

14m · 2d ago
📺AI Engineer ·

1 Trillion Phone Calls/yr, 10% Error rate: The Crisis in Voice AI — Sumanyu Sharma, Hamming AI

16m · 3d ago
📺AI Engineer ·

Harness Engineering: Building the Production Cage for Powerful Domain Agents — Mike Chambers, AWS

20m · 3d ago
📺AI Engineer ·

Tokens Should Have Jobs — Katelyn Lesse & Angela Jiang, Anthropic

13m · 3d ago
📺AI Engineer ·

Loophole: Adversarial Agents To Stress Test Your Morality — Brendan Rappazzo, Morgan Stanley

16m · 3d ago
📺AI Engineer ·

Total Recall: Agent Memory and Harness Engineering — Ignacio Martinez, Oracle

1h 0m · 3d ago
📺AI Engineer ·

Every step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate

20m · 3d ago
📺AI Engineer ·

Pinecone 2.0 — Edo Liberty, Pinecone

19m · 4d ago
📺AI Engineer ·

Stop Chunking Like It's 2022 — Yuval Belfer, AI21 Labs

18m · 4d ago