Staff ML Engineer - End-to-End Healthcare AI

Devconnectplatform; Northern (KY); On-site; USD 150,000 - 230,000; Full time

Job summary

Bayesian Health is seeking a Staff Machine Learning Engineer to own end-to-end real-time models in a live clinical AI product. You’ll prototype, productionize, deploy, and monitor models across AWS, writing production-grade Python and SQL code, and building ML infrastructure (MLOps).

You’ll work with clinicians and engineers to translate clinical use cases into scalable systems, maintaining model effectiveness in production and continuously improving latency and accuracy.

Qualifications

• PhD in a relevant field with 3+ years experience, or a Master’s with 5+ years shipping ML based software products.
• Experience owning ML models from prototyping to production.
• Experience writing production-grade Python and SQL code to implement and evaluate ML models in production systems.

Responsibilities

• Prototype and tune innovative, new ML models and labeler systems based on clinical use cases and state-of-the-art ML methods.
• Productionizing: the same models that you develop with production-grade Python.
• Deploying: identify strategies for improving our production ML-based systems and write, debug, and deploy production-grade Python code.
• MLOps: build infrastructure that enables ML model development and deployment in production systems.

Skills

Python

SQL

MLOps

SageMaker

MLFlow

Model prototyping

Production ML

Education

PhD in a relevant field

Master’s in a relevant field

Tools

AWS SageMaker

MLFlow

Job description

Bayesian Health is seeking a Staff Machine Learning Engineer to own end-to-end real-time models in a live clinical AI product. You’ll prototype, productionize, deploy, and monitor models across AWS, writing production-grade Python and SQL code, and building ML infrastructure (MLOps).

You’ll work with clinicians and engineers to translate clinical use cases into scalable systems, maintaining model effectiveness in production and continuously improving latency and accuracy.