Investigative Web Research Specialist - AI Benchmarking (International) (India)

Investigative Web Research Specialist - AI Benchmarking (International) (India)

02 Sep
|
Braintrust
|
India

02 Sep

Braintrust

India

About The Role

Help build an evaluation benchmark for frontier AI browsing agents. You will design investigative research problems that are difficult for advanced AI systems to solve, even with web access, and document a complete, auditable evidence trail.

What You'll Do

- Create natural-language research questions with short, stable, objectively verifiable answers.

- Develop independently checkable clues across people, places, dates, organizations, works, events, records, and quantities.

- Locate and cite primary records in government and institutional databases, archives, registries, and PDF documents.

- Record the searches you performed and produce precise, structured documentation that another reviewer can audit.

Requirements

- A master's degree or at least 3 years of relevant experience.

- Experience in at least one of these areas: librarianship or archival research; investigative journalism or fact-checking; OSINT, due diligence, KYC, or investigative research; patent, prior-art,



or legal-discovery search; genealogy or records research; or competitive quizzing or puzzle-hunt construction.

- Strong open-web research skills and comfort investigating unfamiliar subjects from scratch.

- Native or near-native written English.

- Exact sourcing at the page, table, and section level.

- Experience with LLM evaluation, red-teaming, or benchmark construction.

Nice to Have

- Familiarity with JSON and structured data formats.

Engagement

- Remote contractor project expected to last 8 weeks.

- Availability for 40 hours per week, including at least 4 hours of Pacific Time overlap.

- Work volume is project-dependent, and weekly paid hours are not guaranteed.

- Selected applicants will complete an assessment and delivery-manager review.

Payment

- $30 per approved task. The estimated average handling time is 3 hours per task. Actual hourly earnings vary with task availability, approval, and completion time.

📌 Investigative Web Research Specialist - AI Benchmarking (International) (India)
🏢 Braintrust
📍 India

Reply to this offer

Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.

Subscribe to this job alert:

Get the latest job offers by email for: investigative web research specialist - ai benchmarking (international) (india) / india

Subscribe to this job alert:

Get the latest job offers by email for: investigative web research specialist - ai benchmarking (international) (india) / india