Back to jobs
Job Description
- Lead the definition and execution of quality metrics for the Shopping Agent, ensuring response accuracy, safety, and brand alignment across multimodal interactions (e.g., text, voice, and image).
- Design and implement automated evaluation pipelines and "golden datasets" for complex shopping journeys, including virtual try-on, reasoning, and support queries.
- Collaborate with research and modeling teams to perform quality evaluations for foundational models, optimizing prompts and grounding to reduce hallucinations and improve conversion outcomes.
- Develop integration tests for agentic actions (e.g., add-to-cart and checkout).
- Ensure seamless interoperability between the Shopping Agent and Customer Service Agent platforms.