Domain Contributor - Evaluation Specialist

$30–60/hr

rate as listed

Workload: ~15 hrs/week
Engagement: Project-based
Location: Worldwide
Field: Sciences

Design domain-specific tasks that expose reasoning and sourcing failures in advanced AI models, then assess model outputs against authoritative evidence. This remote contract is aimed at experts in history, archival or library science, law, finance, journalism, or technology and industry history who have relevant AI training or evaluation experience.

What the work involves

You will create difficult questions and realistic scenarios in your area of expertise, assess AI-generated responses, and verify claims against authoritative and primary sources. Each submission requires a clear rationale identifying reasoning gaps, source errors, factual inaccuracies, or missing domain nuance. Work is completed independently and submitted on a rolling basis under detailed guidelines and evaluation rubrics.

What micro1 screens for

The screening is likely to test whether you can demonstrate deep expertise in history, archival or library science, law, finance, journalism, or technology and industry history through specific examples and follow-up questions. Expect scrutiny of your hands-on experience with AI model training, annotation, RLHF, evaluation, or adversarial task design, as well as your ability to distinguish a merely imperfect answer from one that fails on evidence or reasoning. Graduate-level research, Fortune 100 experience, and professional fluency in a non-English language are stated as additional advantages, not requirements.

Practical logistics

This is a remote contractor role with flexible, pay-per-task work and an expected workload of approximately 15 hours per week. The workflow appears largely asynchronous, but minimum weekly submissions apply, and the exact minimum is not disclosed. Selected contributors are expected to begin their first tasks within 24 to 48 hours after onboarding. Compensation depends on tasks meeting project specifications, so the posted band should not be treated as a guaranteed rate.

Pay band: $30–60/hr

What they look for

Domain depth
Source verification
Reasoning clarity
Evaluation expertise

Included with this listing

Interview prep — 10 questions

Matched to what this platform's screening actually measures. Answer each out loud in 60–90 seconds: claim → concrete example → implication.

What it tests: This tests whether your expertise is grounded in identifiable work, research, publications, cases, transactions, investigations, collections, or technical projects rather than broad interest in the subject.
A strong answer: Anchor the answer in a defined specialty, concrete responsibilities, and representative work products, then explain which types of model outputs you can assess confidently. Be explicit about the boundaries of your expertise as well as its depth.
Where people lose it: Candidates lose points by naming a broad field, such as law or finance, without identifying a practice area, research focus, source base, or substantive work they personally performed.

Summary, eligibility guidance and screening preparation are prepared by Sidequest from the platform's posting. Check the source listing before applying.