Remote AI Research Associate: Benchmarking & OSINT

Crossing Hurdles; Indonesia; On-site; IDR 30,000,000 - 54,000,000; Full time

Job summary

Crossing Hurdles in Indonesia seeks an experienced researcher to design and verify AI benchmarks, investigate facts, and test model reasoning. You will craft tasks, evaluate model outputs, and provide primary-source-backed keys for rigorous QA.

Strong OSINT and writing skills are essential. Ideal candidates have deep experience in investigative research, fact-checking, and AI benchmark development, with a track record in red-teaming or technical QA.

Qualifications

• Strong experience in investigative research, fact-checking, AI benchmark authoring, red-teaming, or technical QA.
• Web research and OSINT skills across academic archives, local records, and specialized databases.
• Ability to analyze model search trajectories and identify failures.

Responsibilities

• Investigate hard-to-find facts and verify information through credible sources.
• Design challenging research tasks to test AI models.
• Test AI model outputs and identify failures in search and reasoning.
• Analyze model search trajectories, source selection, and reasoning failures.
• Write clear benchmark prompts and accurate, primary-source-backed answer keys.

Skills

Investigative research

Fact-checking

AI benchmark authoring

Red-teaming

Technical QA

Job description

Crossing Hurdles in Indonesia seeks an experienced researcher to design and verify AI benchmarks, investigate facts, and test model reasoning. You will craft tasks, evaluate model outputs, and provide primary-source-backed keys for rigorous QA.

Strong OSINT and writing skills are essential. Ideal candidates have deep experience in investigative research, fact-checking, and AI benchmark development, with a track record in red-teaming or technical QA.