Clinical Data Engineer

Summary

Eight Sleep is a company on a mission to fuel human potential through optimal sleep, redefining wellness through advanced technology. The Clinical Data Engineer will own the end-to-end data pipelines for clinical studies, creating monitoring tools, aligning datasets, and conducting data analysis to support product decisions and improve research efficiency.

Responsibilities

• Build and maintain scalable ETL pipelines using Python, SQL, and APIs to ingest and process large-scale biometric and sensor data
• Design data models and workflows that support clinical studies, internal tools, and downstream analytics
• Manage data storage, retrieval, and archival systems in AWS, including handling long-term access and data restore workflows
• Ensure data integrity, reproducibility, and proper versioning across evolving datasets and analyses
• Leverage AI-assisted tools to accelerate data analysis, debugging, and code development, improving iteration speed and reducing manual effort
• Analyze sleep, physiological, and behavioral datasets to evaluate product performance and validate new features
• Perform statistical analyses (e.g., correlation, error metrics, bootstrapping, validation frameworks) to assess algorithm accuracy and clinical outcomes
• Develop evaluation pipelines for metrics like HR/HRV accuracy, presence detection, and sleep staging
• Build tools and structured datasets to support training and validation of machine learning models, integrating multiple data sources for supervised learning
• Investigate edge cases, sensor issues, and data anomalies to improve model robustness
• Maintain and extend Python-based applications for visualizing and annotating biometric data
• Develop interactive tools for researchers and engineers to inspect sessions, validate signals, and debug algorithms
• Streamline workflows for clinical teams to reduce manual effort and improve reproducibility
• Partner with Machine Learning, Hardware, Firmware, and Product teams to build algorithms and test prototypes
• Work with Growth and Product teams to explore user behavior and inform feature development
• Synthesize findings into reports, dashboards, and presentations for internal teams and external audiences
• Contribute to abstracts, posters, and conference presentations; communicate uncertainty, methodology, and tradeoffs clearly to guide decision-making

Skills

• 2+ years of data engineering experience with health/physiology data in a research context — you've built ETL pipelines around messy, real-world biometric or sensor datasets, not just clean CSVs
• Advanced Python and SQL proficiency — Pandas, NumPy, time-series analysis, and production-quality scripting are daily tools, not occasional ones
• Intermediate-to-advanced signal processing and biometric data experience — you've worked directly with heart rate, HRV, sleep staging, or similar physiological signals from wearable or embedded sensors
• Intermediate-to-advanced statistical modeling and validation skills — you can design and execute correlation analyses, error metrics, bootstrapping, and validation frameworks independently
• Working proficiency with AWS and Snowflake — you've built or maintained cloud-based data storage, retrieval, and archival systems, not just queried them
• Experience with clinical or regulatory trial data, familiarity with GCP/ICH guidelines, or prior work supporting FDA submissions
• Background in ML model validation or building structured training datasets for supervised learning
• Fluency with AI-assisted development tools (Claude, Cursor, ChatGPT, Copilot) as part of your daily workflow
• Domain knowledge in sleep science, biometrics, or wearable/embedded sensor data
• Experience integrating internal and third-party APIs into unified data pipelines
• Strong cross-functional communication skills — ability to translate complex analyses into clear insights for non-technical stakeholders

Qualifications

Must Haves

• 2+ years of data engineering experience with health/physiology data in a research context — you've built ETL pipelines around messy, real-world biometric or sensor datasets, not just clean CSVs
• Advanced Python and SQL proficiency — Pandas, NumPy, time-series analysis, and production-quality scripting are daily tools, not occasional ones
• Intermediate-to-advanced signal processing and biometric data experience — you've worked directly with heart rate, HRV, sleep staging, or similar physiological signals from wearable or embedded sensors
• Intermediate-to-advanced statistical modeling and validation skills — you can design and execute correlation analyses, error metrics, bootstrapping, and validation frameworks independently
• Working proficiency with AWS and Snowflake — you've built or maintained cloud-based data storage, retrieval, and archival systems, not just queried them

Nice to Haves

• Experience with clinical or regulatory trial data, familiarity with GCP/ICH guidelines, or prior work supporting FDA submissions
• Background in ML model validation or building structured training datasets for supervised learning
• Fluency with AI-assisted development tools (Claude, Cursor, ChatGPT, Copilot) as part of your daily workflow
• Domain knowledge in sleep science, biometrics, or wearable/embedded sensor data
• Experience integrating internal and third-party APIs into unified data pipelines
• Strong cross-functional communication skills — ability to translate complex analyses into clear insights for non-technical stakeholders

Benefits

• Full access to health, vision, and dental insurance for you and your dependents
• Supplemental life insurance
• Flexible PTO
• Commuter benefits to ease your daily commute
• Paid parental leave
• List of benefits may vary depending on your location