Today we’re joined by Vladimir Bychkovsky, Engineering Manager at Facebook, to discuss Spiral.
Subscribe: iTunes / Google Play / Spotify / RSS
Spiral is a system they’ve developed for self-tuning high-performance infrastructure services at scale, using real-time machine learning. In our conversation, we explore the ins and outs of Spiral, including how the system works, how it was developed, and how infrastructure teams at Facebook can use it to replace hand-tuned parameters set using heuristics with services that automatically optimize themselves in minutes rather than in weeks. We also discuss the challenges of implementing these kinds of systems, overcoming user skepticism, and achieving an appropriate level of explainability.
About Vladimir
Mentioned in the Interview
- Spiral: Self-tuning services via real-time machine learning
- Check out all of our great series from 2018 at the TWIML Presents: Series page!
- TWIML Online Meetup
- Register for the TWIML Newsletter
“More On That Later” by Lee Rosevere licensed under CC By 4.0
Franz Franchetti
I’d like to point out the naming clash with our 20 year old and well-known project: http://www.spiral.net