AI eval test case owner (/advisor /partime Cofounder-track / founding team potential/3-10pre week)

We are looking for a part-time AI Evaluation Lead / Test Case Quality Owner for Shopint.We’re building shopping-specific eval test sets for edge, boundary, and robustness failures in AICofounder-track / founding team potential.We are building a decision-impact regression diagnostic for AI shopping and agentic commerce systems.Ideal background:* LLM evaluation, agent reliability, AI quality* Experience with eval rubrics, regression /eval tests, human review workflows, QA, or model behavior analysisWhat you would help with:* Review and improve sample regression case cards* Define candidate evaluator checks * Work with other engineering contributors* Join buyer calls if fit is strong* Help turn buyer feedback into a project scopeTime:3–10 hours/week to start.Compensation:Flexible — paid part-time, advisor equity, founding team role, or cofounder-track depending on contribution and mutual fit. The right person should be comfortable with ambiguity, but serious about building a credible AI reliability eval test case product.