Overview
Hippocratic AI is seeking a PM to lead the development of our model evaluation and data generation platform. In this role, you'll drive the creation of high-quality training and test datasets that inform our model's roadmap and ensure safety in healthcare deployments.
Responsibilities
- Define the strategy and architecture for model evaluation across agent behaviors.
- Collaborate with data scientists, ML engineers, and clinicians to craft robust benchmarks.
- Design and manage internal and external workflows for data labeling and generation.
- Monitor data quality and iterate on tooling and process efficiency.
- Work closely with the model training team to align data feedback loops with product performance.
Qualifications
3+ years in product management with experience in ML evaluation, labeling, or data pipelines.Familiarity with language model datasets, especially in high-stakes or regulated settings.Experience collaborating with labeling vendors, data QA teams, or managing Mechanical Turk-style pipelines.Attention to detail in process design and tooling for human-in-the-loop systems.