Stephanie Lee

Collaborate with engineering and product teams to understand requirements and research questions for conversational AI; perform data annotation, structured rating, and clinical evaluation of mental health LLM outputs to support AI safety and high-quality response behavior; design and iterate prompts for LLMs; build personas and conversational flows to improve coherence, engagement, and task performance; apply evaluation frameworks to test prompt effectiveness and model behavior; analyze model outputs to identify strengths and failure modes; produce detailed reports with results and recommendations.

Rate and assess AI model outputs and safety; review data (text, audio, and visual) against project guidelines; generate prompts for LLMs to create questions/responses; annotate data aligned with project goals; collaborate with team and stakeholders to meet deadlines.

Provide research-based practices for internal clients with emotional, mental, and behavioral issues; support diverse group settings; collaborate with teams to address race, gender bias, social anxiety, mental health, and inequality; crisis management & intervention; client assessments and treatment plans; coordinate with other professionals to ensure consistent care and minimize diversion; consider cultural and linguistic needs.