Fully Remote and Freelance Project- 8-10 hours per week expected as a minimum

This is not a traditional healthcare operations role. You will be helping build better AI by putting your knowledge to work in a structured, flexible, fully remote environment.

The work is long form and self directed, and clear written reasoning matters as much as technical depth.

• Opportunitiy for experienced healthcare operations professionals to evaluate how frontier AI models handle the business side of healthcare:
• Coding an encounter from the documentation, working a denial, auditing a claim, making a prior authorization determination, writing a physician query, or reconciling charges.
• You bring the judgment you have built defending a code set to a payer auditor, catching the unbundled charge, and writing the query a physician will actually answer. We bring the model output that judgment is needed to grade.
• In this role, you will design challenging, realistic tasks drawn from your own practice, such as a coded encounter with rationale and guideline citations, a denial appeal letter, a clinical documentation query, a prior authorization determination, a claims audit report, or a charge capture reconciliation, run them through frontier AI agents, and evaluate what comes back against a professional standard.
• You will work with realistic professional files, the kind a practitioner in your field actually handles, which you assemble yourself.
• Some tasks are compact, built around a handful of files; others are larger scenarios that take several days to build. In every case the goal is the same: a task a competent professional in your field would complete correctly and a frontier model currently gets wrong.

Responsibilities:

• Design challenging, realistic healthcare operations tasks drawn from your own day to day work: the scenario, a prompt phrased the way you would brief a trusted colleague, and the supporting files a professional would need (de identified or constructed encounter documentation, claim forms, remittance advice, payer policies, correspondence), which you author yourself.
• Run those tasks through frontier AI models and evaluate the deliverable they produce (the code set, appeal, query, determination or audit) against the standard you would hold a colleague to.
• Compare two model outputs on identical prompts and files, decide which performed better, and document where each fell short.
• Write detailed grading rubrics that specify what a correct deliverable must contain, such as the right codes at the right specificity, the right guideline cited, the right payer rule applied, and explain in writing why a response passes or fails each one.
• Flag concrete failures with evidence: codes the documentation does not support, wrong sequencing, missed or fabricated guideline references, ignored payer policy, and off brief interpretation of the ask.
• Contribute across coding, CDI, revenue cycle, utilization review and payer operations, and review and refine tasks built by other experts.

Qualifications:

• Hands on experience preferred in medical coding and billing, revenue cycle, health information management, clinical documentation integrity, utilization review and case management, or payer operations.
• Depth in at least one of: inpatient or outpatient coding; professional fee coding; coding audit and compliance; CDI; denials and appeals; prior authorization and utilization review; claims examination; provider credentialing and network operations; practice or revenue cycle management.
• Working understanding of several of the others, enough to know what those workflows involve and how they are run, so you can assess work in an adjacent area and point out what was done correctly or incorrectly.
• Fluent in the code sets and rules of your area (ICD-10-CM and PCS, CPT, HCPCS, DRG or APC logic, payer policy, NCCI edits) and able to cite the guideline behind a decision.
• Coding or HIM credential (CPC, CCS, CCA, RHIA, RHIT, CDIP, CCDS) preferred but not required.

Process:

Assessment- 2-3 hours (unpaid)