This week, Latent Space explored the emerging discipline of inference engineering with Philip Kiely and Ali Taha from Baseten, examining how engineers are learning to optimize and control model behavior in production. The conversation highlighted a critical gap in AI development: while model training has become increasingly commoditized, the practical work of deploying and managing inference at scale remains largely ad-hoc and under-theorized. As inference costs and latency constraints become primary business concerns, the episode underscored why systematic approaches to this layer are becoming essential infrastructure.
Episodes This Week
Get a free sample digest — no signup needed
Real AI summaries from top latent space podcasts, straight to your inbox.
or
No spam, unsubscribe anytime. We'll send one sample digest, then you decide.
Other Weeks
This Week in Latent Space (Jul 27 - Aug 2, 2026)
1 episode · Jul 27 – Aug 2
This Week in Latent Space (Jul 20 - Jul 26, 2026)
2 episodes · Jul 20 – Jul 26
This Week in Latent Space (Jul 13 - Jul 19, 2026)
1 episode · Jul 13 – Jul 19
This Week in Latent Space (Jul 6 - Jul 12, 2026)
1 episode · Jul 6 – Jul 12
This Week in Latent Space (Jun 29 - Jul 5, 2026)
1 episode · Jun 29 – Jul 5
This Week in Latent Space (Jun 22 - Jun 28, 2026)
2 episodes · Jun 22 – Jun 28
This Week in Latent Space (Jun 15 - Jun 21, 2026)
2 episodes · Jun 15 – Jun 21
This Week in Latent Space (Jun 1 - Jun 7, 2026)
5 episodes · Jun 1 – Jun 7
This Week in Latent Space (May 25 - May 31, 2026)
2 episodes · May 25 – May 31
This Week in Latent Space (May 18 - May 24, 2026)
3 episodes · May 18 – May 24
This Week in Latent Space (May 11 - May 17, 2026)
1 episode · May 11 – May 17