AI / ML Engineer

About the role

A small care team cannot read a thousand charts a day. The platform has to learn each person's baseline, notice a drift, and raise the few alerts that matter without crying wolf.

You will own that layer: the personal baselines, the alert logic, the models that score risk, and the evaluation that proves they work before they reach a patient.

What you will do

• Models and rulesDesign, train and deploy the models and rules that turn heart rate, blood oxygen, sleep and activity data into personal baselines and alerts, measured against each member's own numbers, not an average.
• EvaluationMeasure sensitivity, false alarms and drift against labelled outcomes from the care team, and keep the numbers honest.
• ProductionShip models into the live pipeline with monitoring, versioning and rollback.
• Working with cliniciansSit with nurses and doctors to understand which alerts help and which get ignored, and feed that back into the system.
• AI-assisted developmentUse coding agents for the heavy lifting and review their output critically.

What we are looking for

• Three or more years applying machine learning in production, or an outstanding research record. We can flex on years for an exceptional person.
• Strong fundamentals in statistics, time series and anomaly detection. Experience with physiological or wearable data is a strong plus.
• Fluent in Python and the modern ML toolchain, and able to take a model from notebook to a monitored service.
• Rigorous about evaluation. Nothing ships on a hunch.
• Clear communicator who can explain a model's limits to a clinician.

This role is based in Ahmedabad, India.