Engineering Manager, Machine Learning (Safety)

Written by the T&S Network from Discord's posting.

Manages the machine learning team that builds the detection models protecting Discord's 200M+ users from harm, covering real-time and batch models for content understanding, account integrity and platform abuse. The team sits in Trust & Safety and aims to stop harm at a scale manual review cannot cover, with models that make millions of enforcement decisions per day.

• Fraud and scams

What you'd do

• Hire, coach and grow a team of ML engineers, setting expectations for ownership and impact.
• Set the technical vision and roadmap for Safety ML with Trust & Safety, Product, Policy, Legal and Data Science.
• Own production safety models end to end, from defining new capabilities to measuring performance.
• Monitor the operational health of systems making millions of enforcement decisions daily.
• Work with Trust & Safety to improve labels, build golden test sets and automate hand-done investigations.
• Work with other engineering managers to improve the engineering organization.

What it asks for

• 5+ years as a Machine Learning Engineer, Data Scientist or Applied Scientist.
• 3+ years as an Engineering Manager, leading a team of 5+ engineers.
• Practical depth in at least one of abuse or fraud detection, content classification, behavioral or graph modeling, or LLM classifiers.
• Proven record shipping ML systems to production at scale.
• Strong cross-functional communication skills.
• Able to write code hands-on when needed.
• Keeps current with industry trends and new technologies (preferred).

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on Discordnorth_east before you apply. If we got something wrong, report this listing.