AI Analyst & Photographer (Japanese) | Contractor | Worldwide Remote
Turing is seeking Japanese-speaking photographers and data annotators to help build evaluation materials for frontier AI systems. You'll source, modify, and document real-world images to challenge multimodal AI agents in multi-step visual research tasks. This is a fully remote contractor engagement lasting up to 16 weeks, requiring at least 20 hours per week.
About Turing
Based in San Francisco, Turing is the world's leading research accelerator for frontier AI labs and a trusted partner for global enterprises deploying advanced AI. Turing accelerates frontier research with high-quality data, advanced training pipelines, and top AI researchers specializing in coding, reasoning, STEM, multilinguality, multimodality, and agents.
Role Overview
You will create evaluation instances using cropped, occluded, or degraded images of authentic real-world places, products, and media. Each instance is designed to require multimodal AI agents to conduct multi-step web research using tools like Google Search, Google Lens, or reverse image search before accurately generating or restoring missing content.
Key Responsibilities
- Source authentic, high-quality photographs of real-world places, products, and media relevant to the Japanese locale.
- Verify copyright status and document license type and provenance for each image.
- Conduct multi-step research using Google Search, Google Lens, and reverse image search to identify and verify image subjects.
- Create cropped, occluded, masked, or degraded image versions that conceal key identifying details while preserving realistic visual clues.
- Develop clear, time-bound prompts in English without revealing the target identity or answer.
- Prepare concise, objective, one-sentence grading criteria for each evaluation instance.
- Write solution notes documenting the ground-truth identity, research process, supporting evidence, and expected outcome.
Key Qualifications
- Language: Native or highly fluent in Japanese; strong working proficiency in English required for all deliverables.
- Local Cultural Knowledge: Deep familiarity with regionally significant, non-touristy landmarks, universities, municipal buildings, and domestic film and media in Japan. This is a critical requirement.
- Research Skills: Comfortable conducting iterative, multi-step investigative research using Google Search, Google Lens, and reverse image search.
- Image Sourcing & Copyright Literacy: Able to source and verify copyright-free or explicitly licensed imagery from platforms such as Wikimedia Commons, Creative Commons, Smithsonian Open Access, or use original photography.
- Basic Image Editing: Able to crop, mask, or obscure source images while preserving realistic secondary visual clues.
- Attention to Detail: Skilled at writing concise, objective rubric criteria and appropriately time-bound prompts.
- Tool Proficiency: Comfortable working with shared Google Drive folders, file-naming conventions, and structured deliverable submissions.
Education & Experience
- Bachelor's degree or equivalent practical experience in any field.
- Experience in AI evaluation, data annotation, content review, or quality assurance is preferred but not required.
Engagement Details
- Type: Contractor
- Duration: Up to 16 weeks
- Commitment: Minimum 20 hours/week, at least 4 hours/day, with 4 hours of overlap with Pacific Time.
Evaluation Process
Shortlisted candidates will receive a Job Interest Form. Final selected candidates will be contacted with next steps, including consent and onboarding requirements. Candidates must be willing to grant necessary app-integration permissions and complete all standard consent forms and non-disclosure agreements.
