Abstract
Date
Tuesday Nov 17 / 05:05PM PST ( 50 minutes )
Location
Seacliff D
Video
Video is not available
Slides
Slides are not available
Unconference: Engineering AI Systems
From the same track
Session
Progressive Failure Modes of Modern AI Serving Systems
Tuesday Nov 17 / 10:35AM PST
Inference platforms fail in layers. Most organizations focus on model quality while underestimating the systems engineering required to operate production AI workloads safely and reliably at scale.
Abi Aryan
AI Infrastructure Engineer and Educator
Session
The Revenge of the Data Scientist: Why Reliable AI Needs Evals, Traces, and Metrics
Tuesday Nov 17 / 11:45AM PST
Most teams can now ship an AI prototype by calling a foundation-model API. The hard part is knowing whether that system works when real users, messy data, and business consequences arrive.
Hamel Husain
Machine Learning Engineer, 20+ Years in Applied AI, Machine Learning, and Data Science
Session
Skills, Memory, or Fine-Tuning? The Engineering Loop Behind Self-Improving Agents
Tuesday Nov 17 / 01:35PM PST
As agents become mainstream, everyone wants to improve theirs either by making fewer mistakes on existing tasks or by taking on harder ones. This usually happens once an agent is already deployed in production.
Abhinav Sinha
CEO @Lucidic AI, Previously @Stanford AI Lab, @Citadel and Susquehanna International Group, and @Apple
Session
Inside an In-House Data Agent
Tuesday Nov 17 / 02:45PM PST
Details coming soon.
Session
Performance Engineering in the Age of AI
Tuesday Nov 17 / 03:55PM PST
Details coming soon.