Artwork for podcast Machine Learning Engineered
Shreya Shankar: Lessons learned after a year of putting ML into production
Episode 920th October 2020 • Machine Learning Engineered • Charlie You
00:00:00 01:24:00

Share Episode


Shreya Shankar is a Machine Learning Engineer at Viaduct AI. She's a master's student at Stanford and has previously worked at Facebook and Google Brain. She writes some truly excellent articles about machine learning on her personal blog,

Want to level-up your skills in machine learning and software engineering? Join the ML Engineered Newsletter:

Comments? Questions? Submit them here:

Follow Charlie on Twitter:

Take the Giving What We Can Pledge:

Subscribe to ML Engineered:


01:30 Follow Charlie on Twitter (

02:40 How Shreya got started in CS

06:00 Choosing to concentrate in systems in undergrad (

12:25 Research at Google Brain on fooling humans with adversarial examples (

18:00 Deciding to go into industry instead of pursuing a PhD (

19:35 Why is putting ML into production so hard? (

25:00 Best of the research graveyard

29:05 Checklist for building an ML model for production

34:10 Ensuring reproducibility

39:25 Back to the checklist

44:25 PM for ML engineering

48:50 Monitoring ML deployments

53:50 Fighting ML bias

58:45 Feature engineering best practices

01:02:30 Remote collaboration on data science projects

01:07:45 AI Saviorism (

01:17:40 Rapid Fire Questions


Why you should major in systems

Adversarial Examples that Fool Both Computer Vision and Time-Limited Humans

Choosing between a PhD and industry for new computer science graduates

Reflecting on a year of making machine learning actually useful

Get rid of AI Saviorism

Designing Data Intensive Applications