Senior Software Engineer — AI Evaluation (Remote)

Prolific; Wales; Remote; GBP 51,000 - 73,000; Full time

Job summary

Prolific invites Computer Science Specialists to join our Expert Network to train and evaluate AI models. You will undertake a quick 10–15 minute test to demonstrate your skills and be invited as a paid participant.

Expect competitive pay rates, flexible hours, and the ability to work from home. As a member, you’ll help train AI by evaluating technical prompts, reviewing research papers, and verifying data and code.

Qualifications

• Educational background with a BSc in Computer Science or closely related field.
• Strong technical literacy to interpret research papers, understand algorithms, and review code logic.
• Analytical mindset with high cognitive ability and attention to details in technical material.
• Professional verification via a valid LinkedIn profile to confirm degree and background during screening.
• Requires a PayPal account to receive payment from clients.

Responsibilities

• AI Evaluation & Ranking: compare AI-generated responses to technical prompts and rank by accuracy, logic, and safety.
• Scientific Review: assess CS research papers alongside AI-generated summaries for integrity.
• Fact-Checking: identify inaccuracies where AI misinterprets data, formulas, or findings.
• RLHF: provide human ground truth to help models align with software engineering and data science standards.
• Code & Logic Verification: audit AI-generated code snippets and diagrams for correctness.

Skills

CS research background

Technical analysis

Code interpretation

Analytical mindset

Education

BSc in Computer Science

Job description

Prolific invites Computer Science Specialists to join our Expert Network to train and evaluate AI models. You will undertake a quick 10–15 minute test to demonstrate your skills and be invited as a paid participant.

Expect competitive pay rates, flexible hours, and the ability to work from home. As a member, you’ll help train AI by evaluating technical prompts, reviewing research papers, and verifying data and code.