Research Evaluation Specialist
Y
YO AI LabsAI evaluation
Source API remote eligibility restrictions: United StatesPart-Time
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Languages
- Strong written communication skills in English
- Required Skills
- Research
Requirements
- Have previous experience in AI training, data labeling, or AI model evaluation.
- Hold a completed Master's or PhD, be an active doctoral candidate, or have equivalent research experience in the relevant discipline.
- Demonstrate scholarly research experience and advanced subject-matter expertise.
- Be familiar with primary academic literature.
- Be able to locate, evaluate, and cross-verify information from authoritative sources.
- Have strong written communication skills in English.
- Be able to work independently, manage priorities, and deliver research within a remote working environment.
- Be prepared to begin promptly; selected candidates are expected to start their first tasks within 24–48 hours of completing onboarding.
- Complete the specified minimum number of tasks each week.
Responsibilities
- Develop original, high-difficulty question-and-answer pairs to assess advanced AI model capabilities within your area of expertise.
- Research, verify, and document answers using primary sources, scholarly literature, and authoritative references, including citations and supporting reasoning.
- Design questions requiring advanced reasoning, methodological understanding, and synthesis across multiple sources.
- Test questions against AI systems and iteratively increase the complexity of items that do not adequately challenge the models.
- Write precise, clear, and logically defensible questions and answers.
- Incorporate reviewer feedback and follow project guidelines and quality standards.
- Maintain research integrity, documentation, and analytical rigor across deliverables.
View Full Description & ApplyYou'll be redirected to the employer's site
