Coffee Sessions #60 with Alexandre Patry, Path to Productivity in Job Search and Job Recommendation AI at LinkedIn.
Get the newsletter: https://go.mlops.community/YTNewsletter
// Abstract
A year ago, LinkedIn's job search and recommendation AI teams were at the end of a growth cycle. They were fighting many fires at once: a high number of user complaints, engineers spending a significant amount of their time keeping our machine learning pipelines running, online infrastructure that wasn't supporting their growth, and challenges in ramping up new models to experiment. In this talk, Alex discusses how they all came together to manage these challenges and set themselves for their next phase of growth.
// Bio
Alex has been a machine learning engineer at LinkedIn for almost seven years. He had a tour of duties in LinkedIn Groups, content search, and discovery, feed, and has been tech leading in LinkedIn Talent Solutions and Careers for the last two years.
Prior to working at LinkedIn, Alex lived in Montreal, where he completed a Ph.D. in Statistical Machine Translation, then worked for five years on information extraction.
// Relevant Links
--------------- ✌️Connect With Us ✌️ -------------
Join our Slack community: https://go.mlops.community/slack
Follow us on Twitter: @mlopscommunity
Sign up for the next meetup: https://go.mlops.community/register
Catch all episodes, Feature Store, Machine Learning Monitoring, and Blogs: https://mlops.community/
Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/
Connect with Skylar on LinkedIn: https://www.linkedin.com/in/skylar-payne-766a1988/
Connect with Alexandre on LinkedIn: https://www.linkedin.com/in/patry/
Timestamps:
[00:00] Introduction to co-host Skylar Payne and guest Alexandre Patry
[01:46] Alexandre's background in tech
[02:37] Alexandre's transformation from LinkedIn
[04:48] Feedback from the users at LinkedIn / Transformation Arc
[05:12] Model refactoring
[08:26] Jumping into the unknown vs optimizing what you have
[11:20] Incremental wins
[13:08] Question of trade-off
[14:07] ML engineers don't produce code, they produce knowledge from experimentation.
[15:21] Creating a central repository
[16:37] From user complaints to taking action to a model
[20:48] Pendulum theory at LinkedIn
[21:48] Evolution process over time
[24:00] Why linguists?
[26:14] Transformations of model recommendations
[29:16] Cultural challenges at LinkedIn
[31:20] Pushbacks from users
[32:27] Gathering signals
[34:35] Friction into production
[36:31] Failure that could have been prevented
[38:38] War stories in LinkedIn
[41:53] What's next after no small feat
[43:03] Transformation of engineers on LinkedIn
[46:06] De-risking before diving deep into a project
[47:26] Advice to junior engineers with MLE
[50:22] Hiring at LinkedIn!
