Senior ML Engineer, Health AI — End-to-End Model Ownership

Circadia Health; El Segundo (CA); On-site; USD 150,000 - 240,000; Full time

Benefits offered by this job

Meaningful stock options

100% medical coverage

401(k)

Generous time off

Team events & culture

Job summary

Circadia Health in El Segundo, CA seeks a Senior Machine Learning Engineer to own end-to-end model development from data to deployment. You will design, train, and evaluate clinical prediction models using time-series vital signs and EHR context, define ground truth with clinical teams, and ensure robust evaluation and backtesting.

Role involves production-scale ML Ops, monitoring real-world performance, and contributing to regulatory submissions.

Qualifications

• 5+ years building ML models that reached production and informed decisions.
• Strong Python and modern DL frameworks; 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.
• Ability to present model behavior to non-technical stakeholders.

Responsibilities

• Design, train, and evaluate clinical prediction models with time-series features.
• Define ground truth, build adjudication workflows, and manage targets.
• Build eval harnesses, backtesting, and regression suites for model versions.
• Assess sensitivity, specificity, lead time, and alert burden in deployment.
• Assess performance across facilities, settings, and demographics.
• Ship with ML Ops support and contribute to validation studies and submissions.

Skills

ML production

Python & DL

Time-series

Evaluation & leakage

Backtesting infra

SQL & production data

Stakeholder comms

Job description

Circadia Health in El Segundo, CA seeks a Senior Machine Learning Engineer to own end-to-end model development from data to deployment. You will design, train, and evaluate clinical prediction models using time-series vital signs and EHR context, define ground truth with clinical teams, and ensure robust evaluation and backtesting.

Role involves production-scale ML Ops, monitoring real-world performance, and contributing to regulatory submissions.