Biomedical Data Manager

Partner with leadership in machine learning, biomedical data science, and program management to define how clinical and translational research datasets are governed, structured, and scaled. Own the vision for maximizing company platform's capabilities and architect improvements to the system for hosting high-velocity, multi-modal histopathology data. Serve as primary technical authority for digital pathology data domain, interfacing with partners on complex integrations and setting the standard for data excellence across the organization.

Architect and own the end-to-end data management, governance, and quality strategy for large scale, multi-modal clinical programs (including whole slide imaging). Drive the technical roadmap for data platform evolution, partnering with senior leadership (Algorithm Product, Translational Research) to define long-term opportunities and scalable process architecture. Establish technical standards and best practices for data management processes, ensuring consistency and scalability across products and partnerships.

Serve as lead Subject Matter Expert for the digitalization of clinical data, translating complex partner needs into scalable technical requirements for platform teams. Lead the design and implementation of scalable, reusable data models and workflows for novel projects, engineering solutions that minimize bespoke work. Serve as lead technical expert on the internal ML platforms, designing robust solutions for complex deployment, validation, and data integration challenges.

Oversee and automate the successful execution, validation, and lifecycle management of all major algorithm deployments, ensuring data integrity from ingestion to analysis. Innovate and engineer new solutions and tooling to abstract data workflows, improve data quality, and reduce time to delivery. Define and implement the long-term strategy for team tooling and efficiency, identifying, vetting, and championing the adoption of new technologies.

Provide technical leadership and definitive guidance on the team's most complex data-related barriers, fostering a culture of innovation and proactive problem solving. Create and govern the core standards for technical documentation, SOPs, and cross-functional training. Position is fixed location based in Boston, MA office; however, telecommuting from a home office may also be allowed.

Requires a Bachelor’s degree in Biomedical Informatics, Biomedical Engineering, Public Health, Epidemiology, Biostatistics, or a related field plus three (3) years of experience as Staff Biomedical Data Manager or progressive experience in biomedical data management, with a focus on data architecture, curation, and communication. Experience may be gained concurrently and must include:

Two (2) years in each of the following:

• Using Python or R for large-scale data wrangling, statistical modeling, and automated reporting
• Architecting and maintaining production-grade ETL/ELT pipelines using industry standard tools (Spark, Airflow, Databricks, or similar)
• Managing data sets within strict regulatory frameworks
• Data Harmonization and Standardization, specifically mapping disparate data sources to common data models.

One (1) year in each of the following:

• Managing end-to-end Digital Pathology workflows, including ingestion, storage, and metadata extraction for Whole Slide Images (WSI)
• Utilizing CI/CD for data (Git Hub Actions), data monitoring and observability tools, and environment management (Docker)
• Working with medical terminology (oncology and pathology) or clinical trial structure
• Working with oncology-specific data archetypes, including TNM staging, histology codes, and biomarker status
• Working with sensitive data sets.

Alternatively, will accept a Master’s degree and two (2) years of experience.