Remote | Radiologist (MD) — Medical Imaging AI Annotation & Evaluation — $200–$400/hour

We are sharing a specialised consulting opportunity for experienced Radiologists with strong expertise in diagnostic imaging, structured reporting, clinical reasoning, image annotation, and medical-imaging evaluation to contribute to advanced AI training and clinical-evaluation projects.

Selected professionals will apply diagnostic expertise to non-clinical work involving imaging interpretation, structured finding annotation, reference-report authoring, AI-output review, and evaluation-framework development. This role does not involve direct patient care or responsibility for live diagnosis. Contributors join a shared expert pool and may be matched across multiple imaging workstreams based on subspecialty, availability, and project needs.

Key Responsibilities

Clinical Imaging Interpretation

• Review imaging studies alongside relevant patient history and clinical context
• Document diagnostic reasoning rather than providing only a final impression
• Identify clinically significant findings using precise radiological terminology
• Apply subspecialty expertise to common, complex, and atypical imaging cases
• Maintain strong diagnostic accuracy across repeated evaluations

Structured Finding Annotation

• Label discrete imaging findings according to defined project schemas
• Record presence, location, laterality, severity, and interval change
• Apply structured-reporting standards relevant to the imaging modality and subspecialty
• Maintain consistency and precision across annotation tasks
• Support development of high-quality medical-imaging reference datasets

Reference Report & Case Development

• Author reference reports representing appropriate professional interpretations of imaging studies
• Produce clear findings and impressions aligned with clinical reporting standards
• Develop difficult cases designed to test the limits of AI reasoning
• Create imaging questions and scenarios reflecting realistic diagnostic complexity
• Incorporate appropriate clinical context, uncertainty, and differential considerations

AI Output Review & Clinical Quality

• Review AI-generated imaging interpretations against professional clinical standards
• Identify hallucinated findings, missed abnormalities, and unsupported certainty
• Assess diagnostic reasoning, terminology, report structure, and clinical relevance
• Provide structured feedback explaining significant weaknesses or errors
• Distinguish clinically meaningful problems from acceptable stylistic variation

Evaluation Criteria & Guideline Development

• Develop grading criteria and guidelines for consistent imaging-output evaluation
• Define distinctions between excellent, acceptable, and inadequate radiological assessments
• Apply frameworks such as BI-RADS, LI-RADS, Lung-RADS, TI-RADS, or comparable standards where relevant
• Contribute teaching, assessment, and rubric-design expertise
• Support consistent clinical judgement across multiple imaging workstreams

Ideal Profile

• MD or DO with completed diagnostic radiology residency
• Board certification through the ABR or equivalent certifying body in the country of practice, or board eligibility with residency completed
• Active, unrestricted medical licence in the country of practice
• 2+ years of post-residency independent reading experience
• Currently or recently practising with substantial independent-read volume
• Strong command of structured radiology reporting standards
• Precise diagnostic reasoning and image-interpretation skills
• Written and spoken English fluency
• Fellowship training in neuroradiology, musculoskeletal, body/abdominal, chest, breast, or paediatric imaging is advantageous
• U.S. licensure and board certification are particularly valuable
• Medical image annotation, AI evaluation, or dataset-curation experience is beneficial
• Teaching, rubric design, or resident-assessment experience is advantageous
• Published research or sustained technical writing experience is valuable
• Prior AI-training or model-evaluation experience is not required

Engagement Details

• Independent contractor engagement
• Fully remote and open worldwide
• Compensation: $200–$400/hour
• Minimum commitment: 15 hours per week, with the ability to concentrate hours during time-boxed workstreams
• This is a non-clinical engagement with no direct patient care or responsibility for live diagnosis
• Contributors join a shared expert pool and may move between concurrent workstreams based on subspecialty, availability, interest, and project priorities
• Tasks may range from approximately 10 minutes for structured labelling to around 1 hour for full case authoring
• Specific throughput expectations will be provided for each assigned workstream
• Work may involve case interpretation, finding annotation, reference-report authoring, AI-output review, grading-guideline development, and difficult-case creation
• Payments are made weekly through Stripe or Wise based on services rendered
• Projects may be extended, shortened, or concluded early depending on project needs and performance
• H1-B and STEM OPT candidates cannot currently be supported
• Work must be completed without using confidential or proprietary information belonging to any employer, client, healthcare organisation, institution, patient, or other third party

About the Platform

This opportunity is available through 24-MAG LLC. We connect experienced professionals with remote consulting opportunities across technical, evaluation, and project-based workstreams.

By submitting this application, you acknowledge that your information may be processed by 24-MAG LLC for recruitment and opportunity matching in accordance with our Privacy Policy: https://www.24-mag.com/privacy-policy