We are looking for experienced Web Research Specialists to work on an AI evaluation benchmark focused on frontier AI browsing agents.
Experience: 3+ Years
Work Mode: Remote
Engagement: Task-Based
Shift: 7:30 PM – 12:30 AM PST + 4 flexible hours
Availability: Full time, 8 hours/day with 4 hours PST overlap
Key Skills:
- LLM / AI Evaluation
- Web Research & Investigative Research
- JSON & Structured Data
- Red Teaming / Adversarial Testing
- Fact-Checking & Evidence Validation
- Primary-source and institutional research
- Government databases, archives, registries and PDFs
- Exact page, table and section-level sourcing
Role Overview:
You will design challenging research problems that frontier AI browsing agents struggle to solve, even with full web access and multiple attempts.
The work involves starting from a verifiable fact, working backwards to create a difficult research question, and building a complete, auditable evidence trail to validate the answer.
Experience in investigative journalism, professional fact-checking, OSINT/KYC, archival research, patent/prior-art search, legal discovery, genealogy/records research, competitive quizzing or puzzle-hunt construction is highly relevant.
If you have strong research skills and hands-on experience with LLM evaluation, red teaming, or benchmark construction, we’d like to hear from you.
Please share your updated CV and relevant experience for consideration.
📌 Web Specialist (India)
🏢 Sourcebae
📍 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.