Communication Professionals for Prompt and LLM Evaluation

You will help evaluate how language models handle real-world professional communication tasks. The work combines prompt writing with careful review of model responses in a remote, primarily asynchronous setting.

Projects may cover different areas of professional expertise as opportunities become available. You will work independently and use your communication background to judge whether responses are relevant, accurate, useful, and aligned with the task.

• Create prompts grounded in communication and professional language use.
• Evaluate large language model responses for relevance, quality, accuracy, and task alignment.
• Apply editorial judgment to assess model performance.
• Contribute to AI research projects across different professional areas.
• Work independently in an asynchronous project environment.

This is flexible contract, part-time project work for candidates in the United States.

• Time: 20+ hours per week, with no minimum hour commitment.
• Schedule: Flexible and primarily asynchronous.
• Language: Fluent in English.
• Experience: At least five years as an editor, news analyst, reporter, journalist, writer, or author.
• Skills: Strong written communication, editorial judgment, prompt writing, and the ability to assess whether model responses address a professional task.
• Work style: Comfortable working independently.