Position Summary:
This role will be responsible for developing secure, compliant AI infrastructure and reusable frameworks that enable internal teams and external consultants to build and deploy AI agents for Operations, Human Resources, Admissions, and IT, while also supporting advanced LLM-driven clinical and client risk use cases integrated with Beacon's EHR, eMAR, HRIS, CRM, and incident management systems.
Primary Responsibilities:
• Always be compliant with all company and regulatory policies and procedures.
• Design and maintain an enterprise AI Agent framework supporting:
• Task automation
• Data retrieval and summarization
• Workflow orchestration
• Human-in-the-loop approvals
• Build shared services including:
• Prompt management and versioning
• Tool and API integration layers
• Authentication, role-based access, and audit logging
Clinical AI & Client Risk Intelligence
• Develop and support LLM-powered clinical and risk-focused solutions such as:
• Behavioral and incident pattern analysis
• Medication adherence and documentation quality monitoring
• Early-warning indicators for client risk and escalation
• Integrate AI outputs into clinical workflows, dashboards, and alerts.
• Partner with clinical leadership to ensure interpretability and usability of AI insights.
LLM Engineering & MLOps
• Implement and manage LLM integrations including:
• Secure prompt pipelines
• Retrieval-Augmented Generation (RAG) using enterprise data
• Model evaluation and drift monitoring
• Deploy AI services using scalable cloud-native architecture (APIs, containers, CI/CD).
• Optimize performance, cost, and latency across production AI workloads.
Data Integration & Platform Collaboration
• Work with Data Engineering to leverage:
• Microsoft Fabric
• Azure Data Lake
• Power BI semantic models
• Integrate data from:
• EHR and eMAR platforms
Education and Qualifications:
• Bachelor's degree in Computer Science, Engineering, Data Science, or related field.
• 5+ years of experience in software engineering, data engineering, or AI engineering.
• Hands-on experience with:
• LLM APIs and orchestration frameworks
• Prompt engineering and RAG architectures
• API and microservice development
