Web Research Specialist

Turing

14h

About The Position

Turing is building an evaluation benchmark for frontier AI browsing agents. The Web Research Specialist designs research problems that state-of-the-art AI systems cannot solve, even with full web access and multiple attempts. This is investigative research rather than subject-matter expertise or content writing: start with a verifiable fact, work backward to create a question that makes the fact difficult to locate, and substantiate the work with a complete, auditable evidence trail.

Deliverables include a natural-language research question with a short, stable, objectively verifiable answer; independently checkable clues spanning multiple fact types, such as dates, people, places, organisations, works, events, records, and quantities, with specific constraints; and a validation record documenting obvious searches and their results.

The assignment requires 40 hours per week, including at least four hours of overlap with PST, and lasts eight weeks. It is a contractor assignment with no medical or paid leave. Applicants complete an assessment, after which selected candidates are contacted about next steps.

Requirements

• Demonstrated open-web research ability, including locating primary records and navigating government and institutional databases, archives, registries, and PDF documents.
• Precision with sourcing, including citations to exact pages, tables, and sections rather than homepages alone.
• Comfort researching unfamiliar subjects from scratch.
• Native or near-native written English.
• High tolerance for structured documentation; the evidence trail is the majority of the work.
• Commitment of 40 hours per week with at least four hours of PST overlap.

Nice To Haves

• Experience with LLM evaluation, red-teaming, or benchmark construction.
• Experience in reference librarianship, archival research, or special collections.
• Experience in investigative journalism or professional fact-checking.
• Experience in OSINT, due diligence, KYC, or investigative research.
• Experience in patent, prior-art, or legal-discovery search.
• Experience in genealogy and records research.
• Experience in competitive quizzing or puzzle-hunt construction.
• Familiarity with JSON and structured data delivery formats.

Responsibilities

• Design research problems that are difficult for frontier AI browsing agents to solve.
• Work backward from a verifiable fact to construct a challenging research question.
• Create independently checkable clues spanning multiple fact types and incorporating specific constraints.
• Locate and cite primary records, using exact pages, tables, and sections.
• Document a complete, auditable evidence trail.
• Record obvious searches performed and the results they returned.

What This Job Offers

• Education Level: No Education Listed