Description:

Lead the development of an AI coaching experience within Samsung Health, focusing on evaluating AI-generated coaching outputs.
Create a failure taxonomy, validate an LLM judge, and develop a rubric for assessing AI output quality.

Requirements:

Experience in end-to-end evaluation processes for conversational or generated-text outputs.
Background in conversation design, AI product quality, content design, or UX research with qualitative coding.
Ability to document and arbitrate evaluation criteria and guidelines.
Proficiency in using notebooks and spreadsheets for analysis (no production code required).

Work in a remote-first team with over 100 members across 30 countries.
Opportunity to impact the future of health and nutrition technology within a leading global company.