HireArt is supporting a leading AI research initiative in sourcing Research Domain Experts to help shape the next generation of AI training and evaluation. In this role, you will design and assess complex, domain-driven tasks that challenge AI model reasoning and capabilities.
As a Research Domain Expert, you will:
Design challenging, field-relevant problems based on visuals, prompts, datasets, or model outputs
Evaluate AI-generated responses using detailed rubrics
Write or improve evaluation rubrics for complex tasks
Stress-test model reasoning in research contexts
Provide clear, structured feedback on model performance
Required Qualifications
Bachelor’s degree or higher
Professional or academic experience in a related research field (e.g. AI/ML, robotics, neuroscience, etc.)
Experience working with or evaluating LLM systems
Strong scientific writing, analysis, and reasoning skills
Comfortable working asynchronously with strong self-direction
Ability to deliver structured, precise, and logically sound evaluations
Reliable computer and internet connection