Screener Criteria: LinkedIn profile verification required for eligibility
Start Date: TBC
End Date: TBC
Location: Remote (UK/US/CA/AUS)
Type of contract: freelance
Hourly Rate: $40+/hr
Minimum Hours: TBC from Services
Maximum Hours: Subject to availability
Screening compensation: $46/hr (for eligibility test/screener)
About Prolific
Prolific is not just another player in the AI space. We are building the biggest pool of quality human data in the world.
Over 35,000 AI developers, researchers, and organizations use Prolific to gather data from paid study participants with a wide variety of experiences, knowledge, and skills.
The role
We are seeking Computer Science Domain Experts to act as evaluators for a high-level AI verification project. AI models are now generating complex technical summaries, and we need specialists to ensure these outputs maintain scientific integrity and factual accuracy.
We need experts who can navigate dense scientific literature to judge the accuracy and structural integrity of AI-generated graphical abstracts. This is a flexible, ad hoc project where your technical expertise directly influences how AI understands and summarizes complex computer science research.
What you’ll be doing
* Scientific Review: review computer science scientific papers alongside LLM-generated graphical abstracts.
* Fact-Checking: identify issues and inaccuracies where the graphical abstract does not faithfully represent the source scientific paper.
* Expert Verification: use your domain knowledge to ensure that technical concepts are visually and textually summarized correctly.
* Quality Control: help refine the model's ability to produce "enterprise-ready" scientific summaries.
What you’ll bring
* Advanced Academic Credentials: hold a Master’s or PhD in Computer Science.
* Domain Expertise: specialized knowledge in STEM/Computer Science fields.
* Analytical Skills: history with fact-checking tasks and a high level of basic cognitive competency.
* Verification: a valid LinkedIn profile is required to verify your credentials during the screening process.
* Previous experience with AI-related training or evaluation tasks.
* Background in scientific publishing or peer review.
Why join this project?
This is a unique opportunity to act as an expert in the AI-driven scientific revolution. You’ll be teaching the model how to accurately synthesize complex data, providing the technical rigor that algorithms currently lack.
#J-18808-Ljbffr