Applied Healthcare Researcher
About the Company
Protege is building a platform to facilitate the secure, efficient, and privacy-centric exchange of AI training data. Their DataLab team focuses on building and evaluating high-value datasets grounded in real-world workflows to solve the biggest unmet need in AI.
Responsibilities
- Serve as the primary technical and research point of contact for healthcare customer conversations.
- Translate model-development goals into concrete, feasible data strategies.
- Develop and evaluate methods such as fine-tuning, LLM-based extraction, and classification to demonstrate dataset utility.
- Design and run feasibility research to determine if data can support specific model objectives.
- Build evidence bases including benchmarks, validation analyses, and error characterization.
- Evaluate healthcare data variables, labels, and cohort definitions for achievability.
- Identify proxy variables or alternative dataset structures when ideal variables are unavailable.
- Produce reusable research and technical collateral to scale successful workflows.
Requirements
- Advanced degree (PhD or Master's plus 3+ years industry experience) in machine learning, computer science, biomedical informatics, epidemiology, statistics, or a related quantitative field.
- Hands-on experience building and evaluating ML or LLM-based systems for extraction, classification, or prediction.
- Experience working with healthcare data such as claims, EMR/EHR, clinical notes, or imaging.
- Proficiency in Python and SQL.
- Experience designing evaluations for data quality and dataset representativeness.
- Ability to work directly with technical stakeholders to translate ambiguous goals into research plans.
Preferred Qualifications
- Experience working with messy, real-world clinical data.
- Ability to operate effectively on a customer's timeline.
- Interest in building reusable research frameworks rather than one-off solutions.
