Help evaluate AI-generated CDI suggestions and coding recommendations to improve documentation accuracy and train healthcare AI systems. Remote (US), contractor role — 20+ hrs/week at $84/hr for experienced CDI leaders and clinical coders.
Medical & Health
Remote Hourly · $84/hr
$84/hr
Compensation
1 country
Eligibility
Expert
Experience
Jul 10, 2026
Posted
Open to applicants in
United States
Interested in this role?
Create a free OpenTrain account and apply in minutes.
OpenTrain is the #1 platform for finding and building careers in AI training and data labeling. We make specialized AI training work easier to track, apply for, and grow into a durable freelance career so contributors can build profiles and portfolios that showcase their expertise.
Why AI training in healthcare matters
AI training (data labeling / annotation) is the human side of building modern AI — people teach models how to interpret clinical records, recommend codes, and surface accurate diagnoses. This work is remote, flexible, and directly shapes how healthcare AI systems behave in production.
Work is 100% remote and often flexible around other commitments.
Contributors with clinical and coding expertise play a critical role in clinical safety, compliance, and revenue integrity.
The role
As a Clinical Documentation Integrity AI Reviewer you will evaluate AI-generated CDI suggestions, physician queries, and coding recommendations and provide structured clinical feedback to train and refine healthcare AI. The work supports inpatient and outpatient CDI workflows and focuses on accuracy, compliance, and correct capture of diagnoses, procedures, and severity/risk metrics.
What you'll do
Review AI-generated CDI suggestions, physician queries, and coding recommendations for accuracy and compliance.
Support concurrent and retrospective review workflows across inpatient and outpatient settings.
Provide structured annotations and clinical feedback used to build AI training datasets (evaluation and data collection tasks).
Monitor documentation quality metrics such as query response rates, CC/MCC capture, case mix index, and DRG accuracy.
Recommend improvements to physician query processes and documentation education.
Requirements
This role requires deep, hands-on CDI leadership experience and strong clinical-coding expertise. All listed requirements are essential for effective evaluation and feedback on clinical documentation and AI outputs.
Proven experience leading clinical documentation integrity or improvement programs.
Deep knowledge of MS-DRG methodology, CC/MCC hierarchies, and ICD-10-CM/PCS coding.
Familiarity with physician query management and compliant query standards aligned with AHIMA and ACDIS.
Ability to interpret medical records and clinical documentation with precision for accuracy, compliance, and risk capture.
CCDS, CDIP, RN, RHIA, CCS, or a comparable clinical or coding credential.
Familiarity with CDI software platforms and EHR systems (examples: 3M, Nuance, Optum360) is valuable.
Helpful background
The following backgrounds are helpful but not strictly required: HCC risk adjustment, outpatient CDI experience, familiarity with AI-assisted CDI tools, and experience presenting CDI performance metrics to leadership.
How the engagement works
OpenTrain AI is the hiring and contracting organization for this role. This is a contractor, part-time engagement requiring 20+ hours per week. Pay is USD $84 per hour. Work is limited to candidates located in the United States and requires strong written and verbal English skills.
You will complete structured evaluation and annotation tasks (label types: EVALUATION_RATING and DATA_COLLECTION) that directly feed model training and QA. Tasks are remote and require independent, reliable work habits.
Remote US contract for senior RNs or MDs to evaluate AI-generated utilization management, medical-necessity, and care-coordination outputs; $100–$150/hr, typically ~20 hours/week. Provide clinical review, apply InterQual/MCG/Milliman criteria, and annotate outputs to improve AI training datasets.
Join OpenTrain AI to evaluate and improve AI outputs for patient registration, scheduling, insurance verification, and front-end revenue cycle workflows; US-based contract, 20+ hrs/week at $80/hr. Help turn real operational judgments into training data that improves healthcare AI.
Lead reviews of AI-generated HCC coding and medical records for Medicare Advantage, Medicaid managed care, and ACA risk adjustment workflows. Part-time contractor role (US only) at $110/hr, 20+ hours/week, focused on improving risk score accuracy and RADV readiness.