An introduction to neural network model uncertainty
The past decade has seen a rise in the application of machine learning to all walks of life – from low impact applications like music recommendation systems to high-stakes uses,
Life at Pex
Life at Pex
Auto-scaling an Azure Virtual Machine Scale Set from an external metric source
Recently, the Infrastructure Team at Pex had the pleasure and challenge of shifting all of our deployments from Google Cloud Platform (GCP) to Microsoft Azure.Our services rely heavily on Apache
Pex culture: Focusing on what really matters
Oh, it’s dog-friendly too?! 80s arcade games. Kombucha taps. Fully stocked kitchen. These are the typical bells and whistles we’ve come to expect of tech startups that present as fun,
Interviewing at Pex? Here’s what you can expect during our hiring process
The Pex hiring process So, you applied for a role at Pex (or you are thinking about it), but you want to know what you’re getting into. Don’t worry, you’re
MFCCs: Engineering features from sound
There are many exciting problems that can be solved by training machine learning models on large, audio datasets – distinguishing speakers, identifying instruments in music, and translating speech from one
Reading is good. Reading in order to discuss is better
Learning and continuous development are part of Pex‘s fabric. Not surprisingly, a common way to achieve this is by reading books. I’m pretty sure that I don’t have to convince
Counting distinct values across rolling windows in BigQuery using HyperLogLog++ sketches
How do we count distinct rolling 90 day active users in a data set of billions? At Pex, we actively monitor all visible content on our supported platforms – over
Why we relocated from San Francisco to Los Angeles
Last month, Pex turned 3 years old. But instead of celebrating with a big party, we were busy packing our office and homes, and moving to Los Angeles. Here's why we moved.
