Business Analyst (Computer Use Agent) at Turing

Business Analyst (Computer Use Agent) | Pay varies | Remote | Hourly contract, 16 weeks with possible extension

Turing, a company that works with frontier AI labs on data, evaluations, and reinforcement learning environments, is hiring a Business Analyst for a Computer-Using Agent (CUA) evaluation project. The project assesses and improves how AI systems understand instructions, analyze information, reason through problems, and complete tasks in digital environments. You will review AI-generated responses and actions, validate information through online research, assess accuracy and task completion, identify errors or gaps, and provide detailed annotations, ratings, and explanations.

What the work involves

• Analyzing, summarizing, and structuring complex written content clearly and accurately.
• Conducting online research to verify claims, sources, and supporting evidence.
• Solving analytical, logical reasoning, data interpretation, arithmetic, and puzzle-based questions.
• Creating scenarios and questions to evaluate and improve large language model performance.
• Reviewing AI-generated responses and providing detailed ratings, annotations, explanations, and feedback.

Requirements

• Excellent English communication and reading comprehension skills.
• Analytical, logical, critical, and creative thinking to solve complex problems.
• Ability to identify reliable information and distinguish it from inaccurate or unsupported claims.
• Ability to interpret data, identify patterns, compare information, and perform basic calculations.
• Ability to work independently while following detailed instructions, quality standards, and timelines.

Preferred qualifications

• A degree (held or in progress) in Engineering, Literature, Journalism, Communications, Arts, Statistics, Business, or a related field.
• Experience in business analysis, research, copywriting, journalism, technical writing, editing, translation, or a similar field. Candidates without a bachelor's degree may be considered based on relevant experience and demonstrated skills.
• Familiarity with Excel, Google Sheets, Google Docs, and Google Workspace.
• Interest in artificial intelligence, large language models, online research, and emerging technologies.

Pay and schedule

• Engagement type: hourly, long-term engagement.
• Duration: 16 weeks, with potential opportunities for extension.
• Expected start date: around 15 October.

Hiring process

Selection includes an online assessment that takes about 45-50 minutes and must be completed on a desktop or laptop. Candidates who pass the internal assessment review will be considered for the role.