Senior Machine Learning Engineer

About Circadia Health

Circadia Health is a growth-stage healthcare AI company on a mission to prevent avoidable hospitalizations and transform senior-care operations. Our Circadia Intelligence Platform combines:

• Contactless sensing that monitors respiration and motion with medical-grade accuracy

• Native predictive models that detect 85% of preventable adverse events several days in advance

• Enterprise integrations that operationalize predictions directly inside EHR, care-coordination, billing, and compliance workflows

Today, our technology touches 40,000+ post-acute patients daily across skilled-nursing, home-health, and home-care networks. We are backed by leading healthcare and AI investors and headquartered in El Segundo, CA.

Why this role exists

At most companies the ML engineer supports the product. Here the model is the product, and its accuracy is the ceiling on what the whole platform can deliver.

What we sell is the judgment layer on top of a corpus most teams will never get access to: 70,000 years of continuous vital signs joined to clinical records from more than 400,000 unique patients. You will own the models built on it end to end: what they predict, how they are evaluated, where the threshold sits, and when they ship. Ground truth is retrospective chart review, so your labels are imperfect and you will need to know exactly how.

What you'll own

Model development. Design, train, and evaluate clinical prediction models, with feature engineering across physiological time series and structured EHR context.

Labels and ground truth. Define what you are actually predicting with clinical teams, build adjudication workflows, and understand the noise in your targets.

Evaluation and testing infrastructure. Build the eval harnesses, backtesting, and regression suites that let us ship new model versions and new configurations with confidence, including how flagging behaves and whether explanations hold up.

Clinical evaluation. Sensitivity, specificity, lead time, and alert burden as the care team experiences them. Threshold selection is a clinical decision as much as a statistical one.

Robustness. Find where performance varies across facilities, settings, and demographics, and quantify it.

Production and evidence. Ship with ML Ops support on serving and deployment, monitor real-world performance, and contribute to validation studies and regulatory submissions.

Required Qualifications

5+ years building ML models that reached production and were used for real decisions

Strong Python and modern deep learning frameworks, plus fluency in classical ML

Experience with time-series or sequential data

Evaluation practice covering calibration, class imbalance, and temporal leakage

Experience building evaluation, backtesting, or model regression infrastructure

Strong SQL and experience with production data

Experience presenting model behavior and limitations to non-technical stakeholders

Preferred

Healthcare ML, clinical prediction, EHR data, physiological signals, or early-warning systems

Model validation supporting regulatory submission, or subgroup analysis in a clinical setting

First-author publications, significant open source, competition results, or a high-bar research or engineering background