About The Position

Bask Health is seeking an Applied Scientist, Patient Intelligence to develop machine learning models and data-driven capabilities that help the company understand patient experiences and improve its telehealth platform. The role applies machine learning, statistical modeling, experimentation, and data analysis to operational and behavioral information, including structured datasets, event data, application metrics, and approved patient-related information. The scientist will investigate patient journeys and develop predictive models, segmentation approaches, and intelligent product features. Example areas include onboarding completion, patient drop-off, workflow abandonment, questionnaire completion, and engagement patterns. The position is hands-on and focuses on practical applied science, from defining problems and designing experiments through model evaluation and implementation support. The role works closely with product managers, data specialists, machine learning engineers, and software engineers to establish measurable research questions, evaluate models, communicate findings, and integrate approved capabilities into production applications. The scientist is responsible for appropriate modeling and evaluation methods, careful interpretation of results, and communicating limitations. Because the work involves healthcare-related environments, it requires responsible handling of sensitive information, consideration of privacy and security requirements, and evaluation of potential bias. Patient intelligence systems are intended to support operational and product improvements, not independently make clinical decisions.

Requirements

  • At least 3 years of professional experience in applied machine learning, data science, applied research, or a closely related technical field.
  • Strong programming skills in Python or comparable languages used for machine learning and statistical analysis.
  • Experience developing and evaluating machine learning models using real-world datasets.
  • Strong understanding of supervised learning, classification, regression, and predictive modeling.
  • Familiarity with statistical analysis and experimental design.
  • Experience using Python data science and machine learning libraries.
  • Proficiency with SQL and working with structured datasets.
  • Experience cleaning, transforming, and validating data for analysis and modeling.
  • Understanding of feature engineering and model training workflows.
  • Familiarity with appropriate model evaluation metrics and validation techniques.
  • Ability to identify overfitting, data leakage, and other common modeling problems.
  • Experience conducting exploratory data analysis.
  • Understanding of statistical significance, confidence intervals, and experimental uncertainty.
  • Familiarity with A/B testing or controlled experimentation.
  • Ability to translate product or business questions into measurable analytical problems.
  • Experience communicating technical findings to nontechnical stakeholders.
  • Familiarity with reproducible research and version-controlled development.
  • Understanding of production machine learning considerations.
  • Ability to collaborate with software engineers on model integration.
  • Experience evaluating data quality and identifying inconsistent or incomplete records.
  • Understanding of responsible data use and privacy-conscious analytical practices.
  • Ability to recognize limitations in observational data and model predictions.
  • Strong analytical thinking and problem-solving skills.
  • Excellent attention to detail and documentation practices.
  • Ability to independently own applied research and modeling projects.

Nice To Haves

  • Experience developing machine learning models for healthcare, telehealth, or patient-facing products.
  • Familiarity with patient engagement analytics or digital health product metrics.
  • Experience analyzing onboarding funnels, user journeys, and retention behavior.
  • Experience building propensity models, churn models, or abandonment prediction systems.
  • Familiarity with behavioral segmentation and clustering techniques.
  • Experience with time-series analysis or longitudinal behavioral data.
  • Familiarity with causal inference and uplift modeling.
  • Experience designing and analyzing product experiments.
  • Knowledge of scikit-learn, PyTorch, TensorFlow, XGBoost, or comparable ML frameworks.
  • Experience with experiment tracking and model management tools.
  • Familiarity with feature stores and production ML pipelines.
  • Experience deploying models through APIs or cloud-based services.
  • Familiarity with AWS or comparable cloud platforms.
  • Experience working with event-based application data.
  • Understanding of model drift detection and production performance monitoring.
  • Experience applying natural language processing to approved text data.
  • Familiarity with large language models and modern AI development techniques.
  • Understanding of HIPAA and healthcare data privacy considerations.
  • Experience evaluating fairness and bias in predictive models.
  • Experience using AI-assisted development tools such as Cursor or Claude Code.

Responsibilities

  • Develop machine learning models that support patient experience and operational intelligence.
  • Analyze patient journey data to identify friction points, behavioral patterns, and product improvement opportunities.
  • Build predictive models for approved patient engagement and workflow outcomes, including potential onboarding abandonment and incomplete workflows.
  • Analyze questionnaire completion patterns and other patient interaction signals.
  • Create segmentation models to help product teams understand patient experience patterns.
  • Design machine learning approaches for classification, prediction, and behavioral analysis.
  • Develop feature engineering pipelines using structured application and event data.
  • Build reproducible training, validation, and evaluation workflows.
  • Evaluate model performance using appropriate statistical and machine learning metrics.
  • Design experiments to assess intelligent product features, analyze results, and communicate actionable findings.
  • Collaborate with product managers to define measurable research questions and success criteria.
  • Develop methods for identifying changes in patient engagement and workflow behavior.
  • Work with engineers to integrate approved machine learning capabilities into production applications.
  • Build prototypes demonstrating the practical value of modeling approaches.
  • Evaluate baseline statistical methods against more complex machine learning models.
  • Investigate model errors, data quality problems, and unexpected prediction behavior.
  • Monitor model performance and identify potential data or concept drift.
  • Develop dashboards, reports, and analytical outputs communicating model findings.
  • Collaborate with engineering teams to improve data collection and event instrumentation.
  • Document modeling assumptions, evaluation methodologies, and known limitations.
  • Evaluate models for potential bias, inconsistent performance, and unintended consequences.
  • Ensure appropriate handling of sensitive patient and operational information.
  • Support responsible experimentation and controlled deployment of predictive features.
  • Participate in technical discussions, research reviews, and engineering planning.
  • Stay current with relevant advances in applied machine learning and statistical modeling.
  • Own assigned applied science projects from problem definition through experimentation, evaluation, and implementation support.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service