QA Contractor

• Quality-check evaluation tasks for AI model training and benchmarking as the last independent reviewer before formal review.
• Verify correct answers, supporting evidence, and scoring rubrics for accuracy and completeness.
• Identify and clearly articulate issues with task design, answers, or evidence.
• Confirm claims by cross-referencing sources, checking academic papers, and tracking down original evidence.

This role ensures the accuracy and reliability of AI training data, directly contributing to the development of safer and more trustworthy AI systems.

• Strong attention to detail and ability to identify errors or inconsistencies.
• Experience with research, fact-checking, or quality assurance.
• Ability to communicate findings concisely and escalate issues appropriately.
• Familiarity with academic papers and cross-referencing sources.

Contract position with flexible remote work. Compensation details not specified.

FutureSearch is an organization focused on AI safety and governance, working to improve the quality and reliability of AI systems through rigorous evaluation and benchmarking.