Reliability, Resilience, and ML Serving in Large Scale Systems (Building AI infrastructure for both research and user-facing products, and bridging the gap between) | Kisaco Research

Reliability, Resilience, and ML Serving in Large Scale Systems (Building AI infrastructure for both research and user-facing products, and bridging the gap between)

Speaker(s): 

Author:

Dylan Curley

Engineering Manager
Google

Dylan Curley has spent the majority of his career in AI from a software engineering background. He focuses on large scale AI systems infrastructure, automation, scaling, and reliability. These days Dylan manages a team of SREs (reliability engineers) at Google, who are responsible for the vast majority of AI systems across Alphabet including launching & operating the latest advances in Generative AI (Bard, Workspace, Search, YouTube, etc). He has also spent time working on AI for medical research and astrophysics, and advises startups in AI.

... read more

Dylan Curley

Engineering Manager
Google

Dylan Curley has spent the majority of his career in AI from a software engineering background. He focuses on large scale AI systems infrastructure, automation, scaling, and reliability. These days Dylan manages a team of SREs (reliability engineers) at Google, who are responsible for the vast majority of AI systems across Alphabet including launching & operating the latest advances in Generative AI (Bard, Workspace, Search, YouTube, etc). He has also spent time working on AI for medical research and astrophysics, and advises startups in AI.