Medicine & Clinical Science Expert

Vraify; Deutschland; Remote; EUR 36,000 - 60,000; Full time

Job summary

Vraify is seeking researchers to help evaluate AI models in Medicine and Clinical Science. Remote project-based work, up to $50/hour, depending on project and demonstrated expertise.

You will create, solve, or review expert-level problems across clinical domains, probe AI-generated answers for errors, and produce reference answers and scoring rubrics for audit and validation. These tasks require rigorous reasoning and clear written communication.

Qualifications

• Expert-level knowledge across clinical reasoning, diagnostics, pathology, pharmacology, radiology, and evidence-based medicine.
• Ability to solve difficult problems independently and explain reasoning in clear English.
• Verifiable evidence such as publications, ORCID, or institutional profile.

Responsibilities

• Create, solve, or review expert-level problems in clinical domains.
• Probe AI-generated answers for errors and broken reasoning.
• Produce reference answers, derivations, verification notes, or scoring rubrics.
• Review peer-authored tasks for originality and appropriate difficulty.

Skills

Clinical reasoning

Diagnostics

Pathology

Pharmacology

Radiology

Evidence-based medicine

Medical practice

Independent problem solving

English writing

Job description

Help us find where advanced AI models break in Medicine & Clinical Science. Create or solve difficult, answerable problems, test model reasoning, and explain precisely why an answer succeeds or fails. Remote project-based work can pay up to $50/hour, depending on the project and demonstrated expertise.

What you'll do:

• Create, solve, or review expert-level problems in areas such as clinical reasoning, diagnostics, pathology, pharmacology, radiology, evidence-based medicine, and specialist medical practice.
• Probe AI-generated answers for subtle factual errors, invalid assumptions, missing cases, and broken reasoning.
• Produce reference answers, derivations, verification notes, or scoring rubrics that another expert can audit.
• Review peer-authored tasks for originality, ambiguity, answerability, and appropriate difficulty.

What we look for:

• Deep academic, research, clinical, teaching, or professional expertise in one or more of: clinical reasoning, diagnostics, pathology, pharmacology, radiology, evidence-based medicine, and specialist medical practice.
• Ability to solve difficult problems independently and explain technical reasoning in clear written English.
• Verifiable evidence such as a publication, thesis, ORCID or institutional profile, patent, specialist practice, teaching record, or competition result.
• Prior AI-evaluation experience is useful but not required; domain depth and careful judgement matter more.