Web Research Specialist – AI Research & Evaluation – Kolkata, India
Turn your research skills into work that challenges the limits of AI. Fusion CX is hiring Web Research Specialists in India for a contractual opportunity supporting the evaluation of advanced AI browsing agents. If you have experience in web research, investigative research, fact-checking, OSINT, archival research, or LLM evaluation, this role gives you the opportunity to solve complex research problems, uncover hard-to-find information, and build evidence trails that help evaluate how AI systems search, reason, and find information. This is investigative research, not conventional content writing. You’ll start with a verifiable fact, work backward to create a challenging research question, identify independently verifiable clues across multiple sources, and document exactly how the answer can be validated.
Job Description:
About the Role As a Web Research Specialist, you will contribute to an evaluation benchmark for frontier AI browsing agents. Your work will involve designing research problems that are difficult for state-of-the-art AI systems to solve, even with full web access and multiple attempts. You will start with a verifiable fact and work backward to construct a question that makes that fact extremely difficult to locate. You will then prove your work through a complete, auditable evidence trail. What You Will Produce- A natural-language research question with a short, stable, objectively verifiable answer.
- Clues, each independently checkable, spanning multiple fact types—including dates, people, places, organizations, works, events, records, and quantities—with specific constraints.
- A validation record showing the obvious searches you ran and the results they returned.
- A complete, auditable evidence trail supporting the research.
Job Requirements:
Experience & Eligibility- 3+ years of experience in relevant research or investigative work.
- Native or near-native written English.
- Demonstrated open-web research ability.
- Comfort researching unfamiliar subjects from scratch.
- High tolerance for structured documentation, as the evidence trail is a major part of the work.
- Ability to locate primary records and navigate government and institutional databases, archives, registries, and PDF documents.
- Precision with sourcing, including the ability to cite exact pages, tables, and sections—not just homepages.
- Strong investigative research and analytical skills.
- Ability to construct difficult research questions from verifiable facts.
- Ability to identify and connect independently checkable clues across multiple sources.
- Strong attention to detail when documenting research findings.
- Experience with LLM evaluation, red-teaming, or benchmark construction.
- 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.
- Familiarity with JSON and structured data delivery formats.
Why Join Fusion CX?
What makes this opportunity different is the nature of the research. You won't simply search for information that is easy to find—you'll investigate information that requires persistence, careful source evaluation, and the ability to connect clues across different records and sources. As a Web Research Specialist, you'll work on challenging AI evaluation projects where the quality of your research and evidence trail matters. Your findings will help assess how effectively advanced AI browsing agents handle difficult, multi-step research tasks. What You Will Gain- Gain hands-on experience in frontier AI browsing agent evaluation.
- Apply investigative research techniques to challenging AI benchmark problems.
- Strengthen your expertise in primary-source research, evidence validation, and structured documentation.
- Develop practical experience researching government records, institutional databases, archives, registries, and PDF documents.
- Build experience constructing objectively verifiable research questions and benchmark tasks.
- Strengthen your ability to identify, validate, and connect information across multiple fact types and sources.
- Expand your experience across AI evaluation, LLM benchmarking, web research, OSINT, and investigative research.
