Computer Science Expert (LLM Evaluation)

You will help improve large language models by creating computer science prompts and judging the quality of their responses. The work is remote, flexible, and primarily asynchronous, so you can complete projects independently.

You will also research computer science topics with help from AI and provide expert feedback on whether responses are accurate, clear, and technically sound.

• Create prompts about computer science topics and concepts.
• Evaluate LLM responses for understanding, accuracy, and quality of explanation.
• Research computer science topics with assistance from AI.
• Provide expert judgment to help improve model performance across computer science subjects.

This is part-time project work for contributors in the United States. Project placement depends on availability, and projects operate year-round as they become available.

• Time: 20 or more hours per week.
• Language: Fluent in English.
• Education: Doctoral study, postdoctoral work, or a completed graduate-level academic background in computer science.
• Skills: Strong knowledge of computer science concepts and the ability to explain technical ideas clearly.
• Skills: Ability to assess whether an AI response is accurate and technically sound.
• Work style: Able to work independently in a primarily asynchronous setting.