Web Researcher (AI Benchmarking)

3 hours, 14 minutes ago
Contract
Mid Level
Artificial Intelligence and Machine Learning

Description

  • Design challenging open-web research problems for advanced AI browsing-agent evaluation.
  • Construct multi-step questions from objectively verifiable facts using clues involving people, dates, places, organizations, works, events, records, and quantities.
  • Research government databases, institutional sources, archives, registries, and PDF documents.
  • Create complete, auditable evidence trails citing exact pages, tables, sections, or records.
  • Record validation searches and document the results of obvious search approaches.
  • Test research questions across multiple searches to assess and preserve difficulty.
  • Refine questions to remove ambiguity while maintaining research complexity.
  • Deliver structured and reproducible research documentation.

Requirements

  • Background in reference librarianship, archives, or special collections.
  • Experience in investigative journalism or professional fact-checking.
  • Experience with OSINT, due diligence, KYC, or investigative research.
  • Background in patent, prior-art, or legal-discovery research.
  • Experience with genealogy or historical-records research.
  • Experience with competitive quizzing, puzzle design, or puzzle-hunt construction.
  • Familiarity with JSON or other structured data formats.
  • Availability for 40 hours per week, including at least four hours of overlap with PST.
  • Ability to work remotely from anywhere globally.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

AI Trainer - English-Spanish Bilingual Speaker - Voice Recording

Toloka 251-1K Internet Software & Services

A project-based AI training platform is seeking naturally bilingual English-Spanish speakers to record casual, unscripted voice clips in their everyday speaking style.

3 hours, 14 minutes ago

Native Chinese Speaker Jobs - Voice Recordings, English & Chinese - AI trainer

Toloka 251-1K Internet Software & Services

Record short, natural English-Chinese bilingual voice clips for an AI training platform, sharing everyday thoughts and conversations on a flexible, project-based schedule.

3 hours, 14 minutes ago

Bilingual Professional Side Income - English & Chinese Voice - AI trainer

Toloka 251-1K Internet Software & Services

A project-based AI training platform is seeking bilingual English-Chinese speakers to record natural, unscripted voice clips that reflect everyday code-switching.

3 hours, 14 minutes ago

French Speaking GenAI Content Trust and Safety Experts - Work In Athens, Greece

Mercier Consultancy Professional Services

Mercier Consultancy Group is hiring French-speaking GenAI Content Trust and Safety Experts in Greece to moderate AI-generated social media content and help maintain safe, compliant digital communities.

3 hours, 14 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers