Cardiology Expert - AI Trainer

About the Role

An AI healthcare company that automates administrative and pharmacy workflows to help patients access life-changing medications and specialty treatments is seeking an experienced Cardiology Nurse Practitioner (NP), Registered Nurse (RN), or Physician Assistant (PA) for a part-time consulting role. The role focuses on improving an AI model that identifies patients likely to have transthyretin (ATTR) cardiac amyloidosis through clinical chart review, patient case labeling, and evidence-based clinical reasoning.

What You’ll Do

• Review patient charts and assess the likelihood of ATTR cardiac amyloidosis, including cases with incomplete information.

• Identify relevant clinical signals, including patient history and diagnostic findings such as PYP scans, where applicable.

• Document clear, evidence-based reasoning; distinguish ATTR from similar conditions and maintain consistent labeling standards.

• Refine assessments based on new evidence and AI model feedback, explain clinical decisions to technical teams, and meet labeling deadlines.

Who Should Apply

• NP, RN, or PA with 5+ years of cardiology-focused experience, ideally within a cardiology practice or clinic.

• 1–3 years of experience in a Heart Failure or ATTR-specific clinic.

• Hands-on experience evaluating or managing suspected or confirmed ATTR cardiomyopathy, including PYP scans as appropriate to professional scope.

• Strong clinical judgment and the ability to explain decisions using clear, structured criteria.

• Able to commit 10–20 hours per week alongside clinical practice.

Preferred: Experience at amyloidosis center of excellence or cardiomyopathy clinic; contributions to ATTR-related research or publications; or prior experience with AI/ML teams, clinical decision-support systems, or clinical chart abstraction and labeling.

Project Details

• Engagement: Part-time with a commitment of approximately 10–20 hours per week.

• Required role: US-based clinicians only

• Focus: Patient chart annotation, clinical reasoning, and AI model improvement.