Investigative Web Researcher for AI Benchmarking (Contract)

Turing; San Francisco (CA); On-site; USD 83,000 - 131,000; Full time

Job summary

Turing, a fast-growing AI company in San Francisco, seeks a contractor researcher to design evaluation benchmarks for frontier AI browsing agents. You will start from a verifiable fact, craft an extremely challenging question, and prove your conclusions with a complete, auditable evidence trail.

responsibilities include creating checkable clues spanning dates, people, places, and records, and delivering a structured validation record.

Qualifications

• Demonstrated open-web research ability with primary records and government databases.
• Excellent English writing, native or near-native.
• Experience with LLM evaluation, red-teaming, or benchmark construction.

Responsibilities

• Design research problems that are hard to solve even with full web access.
• Construct an auditable evidence trail with diverse clues.
• Provide a validation record of search methods and results.

Skills

Open-web research

English proficiency

LLM evaluation/benchmarking

Investigative research

Sourcing precision

Tools

JSON

Job description

Turing, a fast-growing AI company in San Francisco, seeks a contractor researcher to design evaluation benchmarks for frontier AI browsing agents. You will start from a verifiable fact, craft an extremely challenging question, and prove your conclusions with a complete, auditable evidence trail.

responsibilities include creating checkable clues spanning dates, people, places, and records, and delivering a structured validation record.