Modal and Scaling AI Inference with Erik Bernhardsson

Modal and Scaling AI Inference with Erik Bernhardsson

1 Min Read

Modal is a serverless compute platform tailored for AI workloads, aimed at allowing AI teams to swiftly deploy GPU-enabled containers, iterate quickly, and autoscale efficiently. The platform was established by Erik Bernhardsson, who previously spent seven years at Spotify developing the music recommendation system and the Luigi workflow scheduler.

In a conversation with Sean Falconer, Erik discusses his motivations for starting Modal, the existing gaps in ML and AI tools, techniques for optimizing container cold starts, the design of Modal’s interface, and more.

Sean Falconer has an extensive background as an academic, startup founder, and former Googler, with published works spanning AI and quantum computing. Currently, he is an AI Entrepreneur in Residence at Confluent, focusing on AI strategy and thought leadership. Connect with Sean on LinkedIn.

Please click here to see the transcript of this episode.

Sponsors

This episode is sponsored by Mailtrap – an Email Platform favored by developers. Enjoy fast email delivery, high inboxing rates, and live 24/7 expert support. Get 20% off all plans with our promo code SEDAILY. Check details in the description below.

You might also like