Tech Stack

Description

You will transform complex policy language into clear operational instructions for human moderators, using AI-assisted content scaling. You'll test policy guidelines against ground truth data and collaborate with cross-functional teams to maintain a safe and inclusive environment for Roblox's community.

Requirements

• Experience using LLMs to create technical documentation, knowledge bases, or process guides
• Understanding of prompt engineering, context windows, and AI output verification
• Proven experience in cross-functional work within Trust & Safety, Content Moderation, or complex Customer Support operations
• Ability to manage shifting priorities and handle time-sensitive critical harms launches with precision
• Comfortable using Quality Alignment scores and Ops metrics to determine policy success

Responsibilities

• Transform complex policy language into clear structured operational instructions for human moderators using prompt engineering and few-shot learning
• Execute policy implementation testing by testing draft guidelines against Gold Label data and ensuring new rules meet enforceability metrics before deployment
• Work with Policy Managers and Product Support to translate safety philosophies into machine-readable logic
• Collaborate with cross-functional teams to identify and address knowledge gaps and improve processes
• Monitor and analyze data to identify areas for improvement in knowledge management and content moderation