{"podcast":{"title":"The CTO Podcast with Fexingo: Technical Leadership, Architecture, and Engineering Org","slug":"the-cto-podcast-with-fexingo-technical-leadership-architecture-and-engineering-org-7871807","podcast_index_feed_id":7871807,"rss_url":"https://feeds.fexingo.com/business/the-cto-podcast.xml","website_url":"https://www.fexingo.com/","image_url":"https://audio.fexingo.com/business/the-cto-podcast/cover.png","author":"Fexingo","episode_count":76,"summary":"Lucas and Luna sit down in front of a whiteboard to dissect the decisions that shape technical organizations. Each episode of The CTO Podcast with Fexingo examines a specific engineering leadership challenge — from scaling a microservices architecture without creating a distributed monolith, to managing the cognitive load of a 200-engineer org, to choosing between a monorepo and polyrepo strategy based on team topology. The conversations are grounded in real-world cases: how Etsy restructured its data pipeline after a 2019 outage, why Stripe’s API versioning policy reduces breaking changes, or what Basecamp’s choice of SQLite over PostgreSQL says about product philosophy. Lucas brings the journalistic rigor — citing commit histories, RFCs, and postmortems — while Luna pushes back with the pragmatics of org dynamics, hiring constraints, and technical debt. There are no hot takes, no vendor pitches, no ‘best practices’ without trade-offs. Each episode ends with a specific tension left unresolved: the optimal number of direct reports for a VP of Engineering, the point at which a monolith should be broken apart, or whether a platform team should own the CI/CD pipeline. The listener is…","last_synced_at":"2026-06-27T14:18:24.326804+00:00","page_url":"https://stenobird.com/podcast/the-cto-podcast-with-fexingo-technical-leadership-architecture-and-engineering-org-7871807"},"episode":{"title":"How Spotify Rebuilt Its Recommender System for 600 Million Users","slug":"how-spotify-rebuilt-its-recommender-system-for-600-million-users","published_at":"2026-06-19T19:36:59+00:00","page_url":"https://stenobird.com/podcast/the-cto-podcast-with-fexingo-technical-leadership-architecture-and-engineering-org-7871807/how-spotify-rebuilt-its-recommender-system-for-600-million-users","show_page_url":"https://stenobird.com/podcast/the-cto-podcast-with-fexingo-technical-leadership-architecture-and-engineering-org-7871807","url":"https://audio.fexingo.com/business/the-cto-podcast/episode-0061.mp3","audio_url":"https://audio.fexingo.com/business/the-cto-podcast/episode-0061.mp3","summary":"In this episode of The CTO Podcast, Lucas and Luna dive into how Spotify rebuilt its core recommender engine from a batch-based collaborative filtering system to a real-time graph neural network serving 600 million users. They explore the specific architectural decisions behind Spotify's migration from Apache Spark and nightly model retraining to a streaming pipeline with TensorFlow and graph embeddings. Lucas explains why the team chose to model user listening sessions as dynamic graphs, how they reduced cold-start latency from hours to under 30 seconds, and the trade-offs they made in compute cost versus recommendation freshness. Luna presses on the practical challenges of A/B testing recommender changes at scale and how Spotify balanced personalization with exploration. The episode also touches on engineering org decisions, including how Spotify structured cross-functional squads around product outcomes rather than model components. By the end, listeners will understand why graph neural networks are becoming the standard for recommendation at tech giants and what it takes to deploy them in production. #Spotify #RecommendationSystem #GraphNeuralNetworks #RealTimeML #MachineLearning #TensorFlow #ApacheSpark #StreamingData #EngineeringOrg #Personalization #ColdStart #ABTesting #Podcast #BusinessPodcast #FexingoBusiness #CTOPodcast #TechnicalLeadership #Architecture Keep every episode free: buymeacoffee.com/fexingo","meta_description":"In this episode of The CTO Podcast, Lucas and Luna dive into how Spotify rebuilt its core recommender engine from a batch-based collaborative filtering sy…","key_points":[],"chapters":[],"topics":[],"duration_seconds":771,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/the-cto-podcast-with-fexingo-technical-leadership-architecture-and-engineering-org-7871807/episodes/how-spotify-rebuilt-its-recommender-system-for-600-million-users/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/the-cto-podcast-with-fexingo-technical-leadership-architecture-and-engineering-org-7871807/how-spotify-rebuilt-its-recommender-system-for-600-million-users.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}