Senior Algorithm Validation Scientist
Overview:
At WHOOP, you will design and execute rigorous validation studies to ensure our physiological sensing algorithms deliver accurate, equitable, and scientifically validated performance. You will partner with scientists, engineers, and product teams to quantify uncertainty and translate evidence into product improvements. This role focuses on evaluating algorithm accuracy, generalizability, and equity across diverse conditions and cohorts, both during development and after deployment. You will drive reproducible analyses and robust validation workflows that enable confident decisions at scale. You'll work in a cross-functional environment to shape high-quality, trustworthy insights that supportResponsibilitiesDesign and execute statistical analyses and validation studies to assess accuracy, precision, reliability, robustness, and generalizability against reference standardsDevelop equivalence and non-inferiority analyses for hardware revisions, manufacturing changes, algorithm updates, and other changes impacting member experienceEvaluate performance across demographic groups, physiological characteristics, environmental conditions, and behavioral contexts to identify disparities and improvement opportunitiesAnalyze experimental and observational production data to understand real-world algorithm behavior using methods like within-subject designs, difference-in-differences, and matchingDevelop reproducible analysis workflows and automated validation processes for consistency across cohorts, hardware revisions, and algorithm releasesPartner with Algorithm Scientists, ML Engineers, Product Managers, Clinical Scientists, and Software Engineers to design validation protocols, establish best practices, and translate evidence into product improvementsKey requirements 3+ years applying statistical methods to complex experimental or observational datasets, preferably in healthcare, wearables, digital health, or related fieldsStrong foundation in statistical inference, hypothesis testing, regression, experimental design, uncertainty quantification, and validation study design; experience with equivalence, non-inferiority, causal inference, method-comparison, or related approaches is a plusProficiency analyzing large datasets using Python, R, or similar tools, with SQL and experience in large-scale data environmentsExperience with physiological, wearable, biomedical sensor, time-series, or longitudinal data; exposure to machine learning or signal processing algorithms is a plusFamiliarity with advanced statistical methodologies such as mixed-effects models, Bayesian statistics, survival analysis, fairness and parity analysisStrong communication and collaboration skills, with ability to translate statistical findings for technical and non-technical stakeholdersCommitment to leveraging AI tools in daily work, ensuring AI-assisted tasks meet high-quality standardsstrong communicationcollaborationcross-functional teamworkPythonRSQL