Responsibilities
- Design and improve artificial intelligence-powered clinical applications in areas such as medical note generation, risk adjustment through HCC coding, clinical decision support, and prior authorization processes by applying clinical knowledge and prompt engineering techniques
- Establish criteria for clinically relevant outputs across product domains, including defining acceptable levels of accuracy, potential failure scenarios, and minimum quality benchmarks
- Partner with interdisciplinary teams including engineers, data scientists, and healthcare providers to embed clinical insights into machine learning models
- Create, assess, and refine input prompts to enhance the performance of AI systems in real-world clinical environments
- Develop and iterate evaluation frameworks to efficiently assess the quality of clinical documentation, with capabilities to detect hallucinations, omissions, and medication-related safety concerns
- Convert clinical requirements into actionable technical requirements and structured data models
- Set clinical safety metrics and baseline measurements; oversee evaluation protocols before and after any model update that impacts clinical outputs
- Support product development, revenue cycle optimization, and other strategic business efforts
- Track updates to clinical guidelines and identify when product functionality must adapt due to new medical standards or payer policies
Work Arrangement
Hybrid — San Francisco, New York, Pittsburgh
Work Arrangement
- Must be willing to work from SF office at least 3x per week
- Position requires a commitment to a hybrid work model, with the expectation of coming into the office a minimum of three times per week
- Relocation assistance is available for candidates willing to move to San Francisco
