Inpatient Medical Coding AI Evaluator

The work

You will evaluate AI-generated clinical documentation and coding outputs against inpatient records, official coding standards, and supporting guidance. Your reviews will help improve the accuracy and completeness of medical AI systems.

The work requires careful analysis of complex records and clear written explanations of coding errors, discrepancies, and difficult cases.

• Review inpatient medical records and clinical documentation for coding accuracy, completeness, and integrity.
• Assign and sequence principal and secondary diagnoses using Official Guidelines.
• Assign Present on Admission indicators and validate MS-DRG assignments.
• Evaluate AI-generated clinical notes, summaries, diagnostic information, and procedure information.
• Identify and resolve diagnosis and procedure coding discrepancies.
• Write clear feedback about errors and complex coding cases.

What it pays and takes

This is a remote, part-time contractor role for candidates in the United States.

• Pay: $50 to $70 per hour.
• Schedule: At least 10 hours per week and less than 20 hours per week.
• Location: Open to candidates in the United States.
• Language: English.
• Certification: An active CIC, CCS, RHIA, RHIT, COC, or another relevant AHIMA or AAPC coding certification.
• Experience: Practical inpatient ICD-10-CM and ICD-10-PCS coding experience.
• Knowledge: Inpatient medical coding, clinical documentation improvement, or a closely related documentation role.
• Resources: Access to current official coding books and Coding Clinic guidance.
• Skills: Careful analysis of complex records and clear written communication of coding findings.

How it works

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training is the human work behind systems that learn from reviewed examples, including medical records and written model outputs. OpenTrain is a platform where people find AI training and data-labeling roles, and specialized expertise matters because it helps produce more reliable evaluations.