Business Analyst (Computer Use Agent)

Turing is a leading company dedicated to advancing superintelligence to foster meaningful economic progress. Based in San Francisco, Turing collaborates with cutting-edge AI laboratories to produce high-quality data, evaluations, and reinforcement learning environments. These efforts enhance AI model capabilities in areas such as coding, reasoning, tool use, and multimodality. Notably, Turing is recognized as the largest and longest-running data provider in the coding category.

The Business Analyst role focuses on a Computer-Using Agent (CUA) evaluation project aimed at assessing and improving AI systems’ abilities to understand instructions, analyze information, reason through problems, and complete digital tasks. This position involves reviewing AI-generated responses and actions, validating information through online research, evaluating accuracy and task completion, identifying errors or gaps, and delivering detailed annotations, ratings, and explanations.

Key Responsibilities:
- Analyze, summarize, and clearly structure complex written content with accuracy.
- Conduct thorough online research to verify claims, sources, and supporting evidence.
- Solve a variety of analytical, logical reasoning, data interpretation, arithmetic, and puzzle-based questions.
- Develop scenarios and questions designed to evaluate and enhance large language model performance.
- Review AI-generated outputs and provide comprehensive ratings, annotations, explanations, and constructive feedback.

Required Qualifications:
- Strong command of English communication and reading comprehension skills.
- Ability to apply analytical, logical, critical, and creative thinking to solve complex problems.
- Skill in identifying reliable information and distinguishing it from inaccurate or unsupported claims.
- Competence in interpreting data, recognizing patterns, comparing information, and performing basic calculations.
- Capacity to work independently while adhering to detailed instructions, quality standards, and deadlines.

Preferred Qualifications and Benefits:
- A degree or ongoing studies in Engineering, Literature, Journalism, Communications, Arts, Statistics, Business, or related fields.
- Relevant experience in business analysis, research, copywriting, journalism, technical writing, editing, translation, or similar disciplines.
- Candidates without a bachelor’s degree may be considered based on relevant experience and demonstrated skills.
- Familiarity with Excel, Google Sheets, Google Docs, and the broader Google Workspace environment.
- A strong interest in artificial intelligence, large language models, online research, and emerging technologies.

Selection Process:
Applicants are required to complete an assessment via a Google Form, accessible through the job application portal. This assessment takes approximately 45-50 minutes and should be completed using a desktop or laptop. Prompt completion of the form is encouraged to ensure consideration for the role. Candidates who successfully pass the internal assessment review will move forward in the selection process.

Project Details:
This is an hourly, long-term engagement expected to last 16 weeks, with potential opportunities for extension. The anticipated start date is around mid-October.

This opportunity offers a chance to contribute to pioneering AI evaluation projects within a dynamic and innovative environment.