Contract evaluator for a Gemini personalization feature: write prompts from your own life, judge whether the model used your Gmail, Search and YouTube history well, and rank side-by-side answers. 4 to 40 hours a week, 3 months, 4 hours of PST overlap. No rate published.
Small business owners write realistic prompts, chat with several AI chatbots (up to 5 turns each) and compare the answers for clarity, usefulness and accuracy. A 16 week project-based contract; you need business documents in English. No rate published.
German-language evaluation of Gemini personalization built on your own Gmail, Search and YouTube activity. Turing contract, remote, $15/hour, 3 months, 4 to 40 hours a week with 4 hours of overlap with PST.
Short Dutch-language evaluation of Gemini personalization, using your own Gmail, Search and YouTube history as test material. Turing contract, remote, $20/hour for 1 month, 4 to 40 hours a week.
One-month Polish-language evaluation of Gemini personalization using your own Gmail, Search and YouTube history. Turing contract, remote, $20/hour, 4 to 40 hours a week, 4 hours of overlap with PST.
Russian speakers test Gemini's personalization using their own Google account data, then rank paired responses on grounding, integration and helpfulness. $15 an hour, 3 months, 4 to 40 hours a week with 4 hours of PST overlap.
Vietnamese-language evaluation of Gemini personalization drawing on your own Gmail, Search and YouTube activity. Turing contract, remote, $15/hour, 3 months, 4 to 40 hours a week.
Thai-language evaluation of Gemini personalization using your own Gmail, Search and YouTube history. Turing contract, remote, $15/hour, 3 months, 4 to 40 hours a week with 4 hours of overlap with PST.
Hindi readers and writers judge how well Gemini uses their own Gmail, Search, YouTube and chat history to personalise answers, ranking response pairs with written reasons. $15 an hour for 3 months, up to 40 hours a week.
Indonesian-language evaluation of Gemini personalization using your own Google data. $15 an hour, 3 months, and a choice of 30 or 40 hours a week (the only variant with a 30-hour minimum), with 4 hours of PST overlap.
Turkish-language evaluation of Gemini personalization on your own Gmail, Search and YouTube history. Turing contract, remote, $15/hour, 3 months, choice of 30 or 40 hours a week, 4 hours of overlap with PST.
Korean-language review of Gemini's personalised answers, built on your own Google activity. Prompt, judge grounding and naturalness, rank paired replies in writing. $15 an hour, 3-month contract, up to 40 hours a week.
Spanish speakers evaluate personalised Gemini responses drawn from their own Google data, ranking paired answers with written rationales. $15 an hour, 3 months, up to 40 hours a week, with 4 hours of PST overlap.
Arabic-language evaluation of Gemini's personalization using your own Google account data: write prompts, check grounding and naturalness, rank response pairs. $15 an hour for 3 months, up to 40 hours a week.
Evaluate Gemini's personalization in Portuguese by testing it against your own Gmail, Search and YouTube history. Turing contract, remote, $15/hour, 3 months, 4 to 40 hours a week with 4 hours of overlap with PST.
Evaluate Gemini's personalization using your own prompts and personal Google data, rank side-by-side responses and write rationales. Contractor, 3 months, 4 to 40 hours a week with 4 hours of PST overlap. No rate published; first posted February 2026.
New roles land most days. Get them on Telegram or Discord as they are added, or read how the platforms pay before you apply.