Senior Machine Learning Engineer

Function Health•Canada, KS

About The Position

Function Health is the AI operating system for health, designed to empower people to live 100 healthy years. We are redefining how individuals understand, measure, and improve their health by moving beyond reactive care and enabling proactive, data-driven insight into human biology. Function has been recognized as one of Fast Company’s Most Innovative Companies of 2024 [https://www.fastcompany.com/91040051/function-health-most-innovative-companies-2024], and is venture-backed by Andreessen Horowitz (a16z) [https://a16z.com/announcement/investing-in-function-health/]. Hundreds of thousands of members have joined Function to take control of their health. Through advanced diagnostics, deep biomarker testing, longitudinal data, and AI-enabled insights, Function equips members with actionable intelligence to take control of both the quality and length of their lives. Function recently announced a $298M Series B and is entering its next chapter of growth. As we scale, the quality and durability of our People systems, data, and insights will directly shape our ability to attract, retain, and support exceptional talent. Function’s newly launched Medical Intelligence Lab (MIL) is charged with building the operating system that converts individual and population health data into health guidance. In essence, MIL is building a GPS for health — a system which understands where you have been, has mapped the health landscape around you, and steers you where you need to go to avoid disease and arrive at healthy longevity. MIL brings together engineers, scientists, physicians, and regulatory and operations experts to build medical world models, prediction models, and guidance models that combine the best of human and machine intelligence. YOUR MISSION As a Machine Learning Engineer in MIL, you will build machine learning (ML) systems that analyze large-scale, multi-modal, longitudinal health data to generate actionable insights for Function users. These ML systems will identify connections between disparate types of data and will analyze the trajectory of that data over time to provide early warning of disease. You will collaborate closely with data engineers, data scientists, and clinical domain experts to ensure that ML systems are reliable, interpretable, and suitable for use in regulated settings involving protected health information.

Requirements

3+ years of experience building and deploying machine learning systems in production.
Strong proficiency in Python and ML frameworks, such as PyTorch, TensorFlow, and scikit-learn (PyTorch is preferred).
Experience with the full model lifecycle: training, evaluation, deployment, and monitoring.
Familiarity with multimodal and/or longitudinal/time-series data (tabular biomarkers, imaging-derived features, events over time, etc.).
Solid understanding of feature engineering, model validation, error analysis, and basic statistical thinking.
Ability to collaborate effectively with data engineering and data scientists in shared data environments.

Nice To Haves

Experience working with healthcare, biomedical, or other regulated data.
Familiarity combining multiple different modalities (e.g., tabular + imaging features, signals + clinical records).
Experience with self-supervised learning and the development of large-scale foundation models.
Experience deploying models in cloud environments (AWS, Databricks, etc.).
Exposure to model interpretability techniques and monitoring strategies (drift, performance degradation, data quality checks).
Experience working in PHI-sensitive and compliance-driven environments.

Responsibilities

Develop, train, evaluate, and deploy machine learning models using multimodal healthcare data (e.g., blood biomarkers, images, medical records).
Partner with data scientists and domain experts to translate clinically informed cohorts, labels, and features into ML-ready representations.
Build and own end-to-end ML workflows, including literature review/prototyping, feature generation, training/validation, inference, experiment tracking and reproducibility, deployment, and monitoring/drift detection.
Design modeling approaches for longitudinal healthcare data, capturing temporal patterns and handling evolving data distributions.
Define evaluation frameworks that prioritize robustness, calibration, interpretability, and stability across cohorts and time.
Contribute to best practices around responsible ML in healthcare, including documentation, auditability, and collaboration with clinical stakeholders.
Support experimentation while maintaining production-quality engineering standards.