FDA-cleared contactless vital monitoring with predictive clinical alerts
Circadia Health operates an FDA-cleared contactless monitoring platform deployed in senior-care settings, combining device telemetry ingestion, EHR integration, and ML-driven risk prediction. The tech stack reveals a heavy investment in ML infrastructure (Airflow, MLflow, XGBoost, LightGBM, SHAP) paired with agentic AI (OpenAI Assistants, LangChain, AutoGen), indicating a shift toward autonomous clinical reasoning and alert generation. Hiring velocity is accelerating across engineering, sales, and newly elevated operations leadership — a pattern typical of post-regulatory clearance scaleout into institutional deployments.
Notable leadership hires: Director of Operations
Circadia Health develops a contactless vital-sign monitoring system for skilled nursing facilities and assisted-living settings. The device measures respiratory rate from up to 8 feet without bed or body sensors, feeding raw telemetry into backend pipelines that integrate with institutional EHRs and apply ML models to surface early-warning signals for conditions like pneumonia, sepsis, and falls — typically hours to days before clinical onset. The company pairs device data with a 24/7 virtual nursing team that reviews alerts and patient history. Founded in 2016 and based in Los Angeles, the company operates at the intersection of medical device regulation, institutional sales cycles, and clinical validation; current work centers on production reliability, multi-site deployment architecture, and reducing avoidable readmissions.
AWS, GCP, Python, Node.js, Kafka, Apache Airflow, MLflow, XGBoost, LightGBM, SHAP, HL7, FHIR, and OpenAI Assistants for agentic alert generation and EHR integration.
Los Angeles, California. The company is hiring in the United States and United Kingdom, with 51–200 employees.
Other companies in the same industry, closest in size
Circadia Health's technology stack, projects, and hiring signals are inferred from public hiring and company data — career pages, public listings, and company web presence — then clustered and de-duplicated. Figures are estimates that refresh over time. Read our full methodology →
This is not an official vendor or customer list. It is a technology-adoption signal inferred from public data, intended for B2B research.