24 days ago
Base Salary
$109k - $167k/yr
Responsibilities
- Define governance, structure, and scaling strategies for clinical and translational research datasets.
- Own the vision and technical roadmap for a platform hosting high-velocity, multimodal histopathology data.
- Architect and govern end-to-end data management, quality, and workflow strategies for clinical programs, including whole-slide imaging.
- Design and implement scalable, reusable data models and workflows that reduce bespoke engineering work.
- Lead technical solutions for machine learning platform deployment, validation, data integration, and lifecycle management.
- Automate algorithm deployment execution and validation while maintaining data integrity from ingestion through analysis.
- Establish technical standards, documentation, SOPs, training, and best practices for data management.
- Evaluate and champion technologies and tooling that improve data quality, workflow abstraction, and team efficiency.
- Provide technical leadership on complex biomedical data challenges and serve as the subject matter expert for digital clinical data.
Requirements
- Bachelor’s degree in Biomedical Informatics, Biomedical Engineering, Public Health, Epidemiology, Biostatistics, or a related field plus three years of experience as a Staff Biomedical Data Manager or in progressively responsible biomedical data management; alternatively, a master’s degree plus two years of experience.
- At least two years of experience using Python or R for large-scale data wrangling, statistical modeling, and automated reporting.
- At least two years of experience architecting and maintaining production-grade ETL/ELT pipelines using Spark, Airflow, Databricks, or similar tools.
- At least two years of experience managing datasets within strict regulatory frameworks and harmonizing disparate data sources to common data models.
- At least one year of experience managing end-to-end digital pathology workflows, including whole-slide image ingestion, storage, and metadata extraction.
- At least one year of experience with GitHub Actions, data monitoring and observability tools, Docker, and environment management.
- At least one year of experience with medical terminology, clinical trial structures, oncology-specific data archetypes, or sensitive datasets.
Benefits
- The position is fixed-location in the Boston, Massachusetts office, with telecommuting from a home office potentially allowed.
- The posting indicates multiple positions are available.
Tech Stack
Categories
Data Engineering
About PathAI
PathAI builds AI-powered pathology software and diagnostic services for biopharma, pathology labs, and health systems to support disease detection, clinical trials, and companion diagnostics. Offerings include machine-learning models for digital histopathology and a CLIA-certified lab operation. Founded in 2016 and headquartered in Boston, it operates as part of Quest Diagnostics and focuses heavily on oncology and immunology applications.