Jon Krohn speaks with Erik Bernhardsson, the man who invented Spotify\u2019s original music recommendation system. They address the different ways to interview a data science candidate, how to deploy a data model into the cloud, and the approach he took that made Spotify go from a digital music startup to an AI-driven streaming giant.\nThis episode is brought to you by Datalore (datalore.online/SDS), the collaborative data science platform, by Zencastr (zen.ai/sds), the easiest way to make high-quality podcasts, and by Bunch (superdatascience.com/bunch), the AI driven leadership coach. Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.\nIn this episode you will learn:\u2022 The data problem that Erik\u2019s company Modal Labs solves [04:32]\u2022 Erik\u2019s prolific blogging career [09:15]\u2022 Opportunities for making data teams more efficient and productive [14:42]\u2022 Erik\u2019s views on interviewing data scientists and software developers [20:18]\u2022 Erik\u2019s tips and tricks for data science interviewees [31:35]\u2022 How Erik built Spotify\u2019s original music recommendation system [38:58]\u2022 Applying vectors to other tools, and opportunities for working with vectors [47:45]\u2022 Using Annoy to search across vectors [50:57]\u2022 Building Python module Luigi for Spotify [55:20]\u2022 The tools that Erik loves to work with [1:06:23]\nAdditional materials: www.superdatascience.com/619