Everlywell is a digital health company pioneering the next generation of biomarker intelligence—combining AI-powered technology with human insight to deliver personalized, actionable health answers. We transform complex biomarker data into life-changing insights—seamlessly integrating advanced diagnostics, virtual care, and patient engagement to reshape how and where health happens.
Over the past decade, Everlywell has delivered close to 1 billion personalized health insights, transforming care for 60 million people and powering hundreds of enterprise partners. In 2024 alone, an estimated 1 in 86 U.S. households received an Everlywell test, solidifying our spot as the #1 at-home testing brand in the country. And we’re just getting started. Fueled by AI and built for scale, we’re breaking down barriers, closing care gaps, and unlocking a more connected healthcare experience that is smarter, faster, and more personalized.
Everlywell operates large-scale health engagement programs that help health plan members complete important care actions — from returning diagnostic kits to accessing preventive and virtual care.
We’re hiring an Applied Scientist to build and measure the ML systems that power these programs. This role is focused on machine learning, experimentation, and production measurement. You’ll train models, evaluate performance, design A/B tests, and work with engineering and business stakeholders to improve real-world outcomes.
This is a high-impact opportunity to apply ML and experimentation skills to systems that influence real member outcomes at scale. You’ll work on practical, production-facing problems with clear business value, strong cross-functional visibility, and room to help shape how Everlywell uses both ML and AI in operational workflows.If you’re excited by hands-on modeling, rigorous experimentation, and building systems that improve decisions in the real world, we’d love to hear from you.
ResponsibilitiesBuild and improve ML models used in engagement and operational workflowsDevelop models for prediction, prioritization, uplift, and related decisioning use casesDefine and monitor model performance, business impact, and system healthDesign and analyze A/B tests and other measurement approaches to evaluate incremental impactPartner with stakeholders to define success metrics and turn findings into decisionsSupport production rollout and ongoing monitoring with engineering teamsHelp evaluate AI- and LLM-powered workflows used in production settings
Skills & Abilities Required:5+ years in Applied Science, Data Science, ML, Decision Science, or similar rolesStrong hands-on experience training, evaluating, and improving ML modelsStrong experience designing and analyzing A/B testsStrong Python and SQL skillsExperience measuring model, program, or product performance in productionAbility to work cross-functionally and communicate clearly with stakeholdersPreferredExperience in experimentation platforms, growth or lifecycle modeling, or ML-driven decision systemsExperience with causal inference or uplift modelingExperience with LLMs, AI agents, or automated workflows in productionExperience in healthcare or regulated environmentsSnowflake, Python, dbt, Airflow, model registry systems, GitLab