Web Research Specialist

Turing • Boston, MA

18h

About The Position

Turing is building an evaluation benchmark for frontier AI browsing agents. The Web Research Specialist will design investigative research problems that state-of-the-art AI systems cannot solve, even with full web access and multiple attempts. This is an investigative research role, not a subject-matter-expert or content-writing role. The specialist starts from a verifiable fact, works backward to construct a difficult-to-find question, and demonstrates the result through a complete, auditable evidence trail.

The work produces natural-language research questions with short, stable, objectively verifiable answers; independently checkable clues spanning multiple fact types and containing specific constraints; and validation records documenting obvious searches and the results they returned. The assignment requires 40 hours per week, including at least four hours of PST overlap, and lasts eight weeks. It is a contractor assignment with no medical or paid leave.

Applicants complete an assessment, which the team evaluates. Selected candidates will be 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 just homepages.
• 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 state-of-the-art AI browsing agents to solve.
• Start from a verifiable fact and construct a challenging research question whose answer is short, stable, and objectively verifiable.
• Develop independently checkable clues spanning multiple fact types, including dates, people, places, organisations, works, events, records, and quantities, with specific constraints.
• Create a complete, auditable evidence trail, citing exact pages, tables, and sections.
• Document validation searches, including the obvious searches run and the results they returned.
• Complete the assessment as part of the application process.

What This Job Offers

• Education Level: No Education Listed