Tech Stack

Description

You will bridge the gap between model capabilities and real product experience by designing prompts, building evaluations, and collaborating with product teams to ensure consistent, safe, and beneficial AI user experiences across all product surfaces.

Requirements

• 5+ years software engineering with Python or similar
• Demonstrated experience with LLMs and prompt engineering
• Strong understanding of evaluation methodologies for AI
• Excellent written and verbal communication
• Ability to manage multiple concurrent projects

Responsibilities

• Design, test, and optimize system and feature-specific prompts
• Build and maintain comprehensive evaluation suites for model quality
• Partner with product, research, and safeguards teams
• Support smooth model launches and catch regressions
• Build frameworks and tools for prompt development and testing