Truly Serverless Infra for AI Engineers - with Erik Bernhardsson of Modal

**Alessio** (0:05)
Hey, everyone, welcome to the Latent Space Podcast. This is Alessio, partner in C2 and resident and decibel partners, and I'm joined by my co-host, Swix, founder of Small AI.

**Swyx** (0:14)
Hey, and today we have in the studio, Erik Bernhardsson from Modal, welcome.

**Erik Bernhardsson** (0:18)
Hi, it's awesome being here.

**Swyx** (0:20)
Yeah, awesome seeing you in person. I've seen you online for a number of years as you're building on Modal, and I think you're just making a San Francisco trip just to see people here, right? I've been to two Modal events in San Francisco here.

**Erik Bernhardsson** (0:33)
Yeah, that's right, we're based in New York, so I figured sometimes I have to come out to capital of AI and make a presence.

**Swyx** (0:40)
What do you think is the pros and cons of building in New York?

**Erik Bernhardsson** (0:43)
I mean, I never built anything elsewhere. I lived in New York the last 12 years. I love the city. Obviously, there's a lot more stuff going on here, and there's a lot more customers, and that's why I'm out here.
I do feel like for me, where I am in life, I'm a very boring person. I kind of work hard, and then I go home and hang out with my kids.
I don't have time to go to events and meetups and stuff anyway. So in that sense, New York is kind of nice. I walk to work every morning five minutes away from my apartment. It's very time-efficient in that sense.

**Swyx** (1:09)
Yeah, yeah.
So it's a good life. So we'll do a brief bio, and then we'll talk about anything else that people should know about you. Actually, I was surprised to find out, you're from Sweden, you went to college in KTH.

**Erik Bernhardsson** (1:21)
Yep, yep.

**Swyx** (1:22)
And your master's was in implementing a scalable music recommender system.

**Erik Bernhardsson** (1:26)
Yeah.

**Swyx** (1:26)
I had no idea.

**Erik Bernhardsson** (1:27)
Yeah, yeah, yeah, yeah. So I actually studied physics, but I grew up coding, and I did a lot of programming competition. And then as I was thinking about graduating, I got in touch with an obscure music streaming startup called Spotify, which was then like 30 people. And for some reason, I convinced them, why don't I just come and write a master's thesis with you, and I'll do some cool collaborative filtering. Despite not knowing anything about collaborative filtering really, but no one knew anything back then. So I spent six months at Spotify basically building a prototype of a music recommendation system, and then turned that into a master's thesis.

**Swyx** (1:56)
Yeah.

**Erik Bernhardsson** (1:57)
And then later when I graduated, I joined Spotify full time.

**Swyx** (2:00)
Yeah, yeah. Yeah. So that was the start of your data career. You also wrote a couple of popular open-source tooling while you were there.
And then you joined, is that correct or?

**Erik Bernhardsson** (2:09)
No, that's right. I mean, I was at Spotify for seven years. It was a long stint. And Spotify was a wild place early on. And I mean, the data space is also a wild place. I mean, it was like Hadoop cluster in the foosball room on the floor. There's a lot of crude, very basic infrastructure, and I didn't know anything about it. And I was hired to kind of figure out data stuff. And I started hacking on a recommendation system, and then got sidetracked in a bunch of other stuff. I fixed a bunch of reporting things and set up A-B testing, and started doing business analytics, and later got back to music recommendation system. And a lot of the infrastructure didn't really exist. There was like Hadoop back then, which is kind of bad, and I don't miss it, but spent a lot of time with that.
As a part of that, I ended up building a workflow engine called Luigi, which is briefly somewhat widely ended up being used by a bunch of companies. Sort of like Airflow, but before Airflow, I think it did some things better, some things worse.
I also built a vector database called Innoi, which for a while was actually quite widely used in 2012 So it was way before all this vector database stuff ended up happening. And funny enough, I was actually obsessed with vectors back then. I was like, this is gonna be huge. Just give it a few years. I didn't know it was gonna take nine years, and then it was gonna suddenly be 20 startups doing vector databases in one year. So it did happen in that sense I was right. I'm glad I didn't start a startup in the vector database space.