ML Engineer

ML Engineer

Role overview

Build and maintain the pipelines that power AI for Solventum’s Healthcare Information Systems (HIS). You’ll ensure ML models work reliably in real-world clinical workflows by bridging data science and software engineering through automated workflows, cloud infrastructure, and secure, scalable AI services.

Key responsibilities

• MLOps & Deployment Pipelines
  • Build and maintain CI/CD pipelines for machine learning (automated testing, model deployment, and version control; e.g., MLflow and Git).
• Model serving
  • Deploy ML models as scalable APIs and microservices meeting performance/latency requirements.
• Monitoring in production
  • Implement monitoring for model performance, data drift, and overall system health.
• Data engineering & integration
  • Develop/optimize ETL pipelines to transform healthcare data (FHIR, HL7) into datasets for training/inference.
  • Help build and maintain feature stores and data layers to keep training vs. production consistent.
  • Collaborate with backend teams to integrate ML outputs into core healthcare applications.
• Engineering best practices
  • Write clean, maintainable, well-documented Python; participate in code reviews.
  • Use Docker and Kubernetes to package and orchestrate ML workloads.
  • Follow HIPAA and HITRUST-aligned security and compliance protocols.

Requirements

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, Data Engineering, or related field.

Nice-to-haves (implied by the posting)

• Strong focus on MLOps, data reliability, and production stability.
• Experience with healthcare data standards (FHIR/HL7) and production ML monitoring.