Machine Learning Engineer

Medical Guardian is a fast-growing digital health and safety company on a mission to help people live a life without limits. With 13 consecutive years on the Inc. 5000 list of Fastest Growing Companies, we’re redefining what it means to age confidently and independently. 

We support over 625,000 members nationwide with life-saving emergency response systems and remote patient monitoring solutions. Trusted by families, healthcare providers, and care managers, our work is powered by a culture of innovation, compassion, and purpose. 

About the Role

Medical Guardian is building a next generation Intelligent Orchestration Engine (IOE), a real-time AI platform that powers proactive engagement, personalization, emergency response intelligence, and member safety.

We are seeking a highly capable Machine Learning Engineer to design, build, and operationalize ML models and pipelines that drive intelligent decisioning across the MG ecosystem. This role will collaborate with Data Science, Engineering, Product, and our AI partners to bring predictive and generative capabilities into production at scale.

You will play a core engineering role in shaping the intelligence layer behind Nexus, Engage360, caregiver insights, emergency workflows, and member engagement.

Key Responsibilities

1. Model Development & ML Engineering

• Build, train, and optimize models for predictions such as churn, fall risk signals, emergency intent classification, and behavioral patterns.
• Implement NLP, embeddings, and LLM-based workflows for contextual understanding of transcripts, messages, and voice interactions.
• Develop real-time scoring services integrated with Azure Event Hub, Service Bus, and IOE rule engines.
• Design reusable, modular components for feature engineering, experimentation, and inference.

2. ML Ops & Deployment

• Build automated training, retraining, and evaluation pipelines in Databricks / Azure ML / Python.
• Develop CI/CD workflows for model deployment using Azure DevOps / GitHub Actions.
• Create scalable inference endpoints using Azure Functions, Container Apps, or APIM.
• Implement monitoring for model drift, data quality, and performance degradation.

3. Data Engineering for ML

• Work closely with Data Engineering to design robust data pipelines.
• Build feature stores, feature pipelines, and data transformations optimized for machine learning.
• Ensure traceability, reproducibility, and well documented data assets.

4. RealcTime Orchestration & Automation

• Integrate ML outputs into real-time orchestration flows.
• Contribute to the IOE decisionctree, scoring logic, and step orchestration.
• Build ML-driven triggers for automated campaigns, safety alerts, and proactive outreach.

5. Collaboration & Strategy

• Work with the Director of Data Science to define the ML roadmap for IOE.
• Partner with Product for personalization, engagement, and predictive feature development.
• Coordinate with Engineering to deliver API endpoints, event triggers, and user facing functionality.
• Contribute to documentation, experimentation logs, governance, and compliance.

Required Qualifications

• 2+ years of experience in Machine Learning, AI Engineering, or similar roles.
• Strong proficiency in Python, ML frameworks (scikit-learn, PyTorch, TensorFlow), and data libraries.
• Hands-on experience with cloud ML workflows (Azure preferred).
• Strong engineering fundamentals: APIs, containers, CI/CD, and distributed systems.
• Experience building and deploying models into production (batch + real-time).
• Understanding of NLP, embeddings, and LLM-based workflows.
• Candidates must be authorized to work in the United States without current or future need for visa sponsorship.
• Must have the ability to work from our Philadelphia office on Tuesdays and Wednesdays.

Preferred Skills

• Experience with Azure ML, Databricks, Delta Lake, Event Hub, Function Apps.
• Experience integrating ML with automation systems (n8n, Logic Apps, Make.com).
• Strong background in data quality, monitoring, and model governance.
• Experience working with healthcare, IoT, or emergency response data.
• Knowledge of prompt engineering, vector databases, or agentic AI workflows.

What You’ll Impact

This role directly affects:

• Proactive emergency response
• Personalized care pathways
• Member safety predictions
• Engagement effectiveness
• Automated decision making
• The intelligence behind the future of Medical Guardian’s platform

You will help build the AI brain of the company.

• Health Care Plan (Medical, Dental & Vision)
• Paid Time Off (Vacation, Sick Time Off & Holidays)
• Company Paid Short Term Disability and Life Insurance
• Retirement Plan (401k) with Company Match