Family Medicine Hospitalist

Scope of Work

1. Review medical records, including FHIR data and clinical notes, for AI training.
2. Check whether clinical information and claims are supported by the medical record.
3. Review inpatient documentation, including HPI, PMH, assessments, and plans.
4. Follow clear guidelines and apply the same standards consistently.
5. Identify missing, incorrect, or inconsistent information in medical records.
6. Share feedback to help improve AI models and data quality.
7. Communicate clearly with the project team about your work and findings.

Preferred Qualifications

1. At least 5 years of hospitalist experience.
2. MD or DO, board certified in Family Medicine (or Family Medicine with a Hospital Medicine focus or certification).
3. Current or recent inpatient/hospitalist experience (within the last 2 years).
4. Strong understanding of inpatient documentation and hospital workflows, including admission, daily progress notes, transitions of care, and discharge.
5. Comfortable reviewing clinical notes and raw medical record data.
6. Strong attention to detail and ability to follow clear guidelines consistently.
7. Experience with chart review, clinical documentation improvement, utilization review, or medical coding/QA is a plus.
8. Experience across a broad patient mix, such as adult medicine, geriatrics, pediatrics, or obstetric/newborn care, is a plus. Family medicine’s cross-population training is especially valuable here.

Compensation Structure

Compensation is output-based; experts are paid per task that meets the project specifications. The time required to complete work may vary depending on the expert’s experience and workflow. Minimum submission requirements apply. Experts must submit a minimum of tasks per week.

Family Medicine Hospitalist Physicians to contribute their medical expertise to a customer project focused on inpatient care and documentation standards. In this role, you’ll apply your broad clinical training to help train next-generation AI systems. Your work will shape how models learn, reason, and perform through high-quality, real-world input.

Originally posted on Himalayas