About this opportunity
Overview
Turing is hiring a Web Research Specialist to help build an evaluation benchmark for frontier AI browsing agents. This role is focused on investigative research: you will work backward from a verifiable fact to design research problems that are difficult for an AI system to solve, even with full web access and multiple attempts. The project is remote, paid in USD, and intended for candidates based in the United States.
The current task mix provides an estimated earning potential of approximately $60 per approved task. The project is expected to run for 8 weeks, with up to 40 hours per week ideally. Candidates who pass the assessment can proceed to onboarding and start as soon as they are successful.
What You'll Do
- Design natural-language research questions with short, stable, objectively verifiable answers.
- Build clue sets that are independently checkable across multiple fact types, such as dates, people, places, organizations, works, events, records, and quantities.
- Create questions that are intentionally difficult to answer, while still being grounded in a known, verifiable fact.
- Produce a complete evidence trail that shows how the answer was verified.
- Document the obvious searches you ran and what results they returned.
Requirements
- Master’s degree or more than 3 years of experience.
- Demonstrated ability to research across the open web, including primary records and government or institutional databases, archives, registries, and PDF documents.
- Strong sourcing precision, with citations to exact pages, tables, and sections rather than only homepages.
- Comfort researching unfamiliar subjects from scratch.
- Native or near-native written English.
- High tolerance for structured documentation, since the evidence trail is the majority of the work.
- Experience with LLM evaluation, red-teaming, or benchmark construction.
Preferred Background
- Reference librarianship, archival research, or special collections.
- Investigative journalism or professional fact-checking.
- OSINT, due diligence, KYC, or investigative research.
- Patent, prior-art, or legal-discovery search.
- Genealogy and records research.
- Competitive quizzing or puzzle-hunt construction.
Nice to Have
- Familiarity with JSON and structured data delivery formats.
Application Process
Submit your application and complete the required assessment. Candidates who successfully pass the assessment will be eligible to proceed with onboarding.
