This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more.

Role Description

The Senior AI Platform Engineer is responsible for architecting, building, and maintaining the agentic software execution layer within Lirio’s Precision Nudging Platform. This position bridges the gap between MLOps and autonomous AI orchestration by engineering the workflows for AI agents to operate securely and reliably.

• Design and implement infrastructure to support LLM-based autonomous agents capable of multi-step reasoning, planning, and task execution.
• Build and manage directed workflows using state machines and tools to coordinate complex AI-human handoffs.
• Lead the architectural design and technical implementation of interoperability standards that enable seamless communication between autonomous agents and diverse software ecosystems.
• Architect and maintain cloud-native platforms that support end-to-end AI workflows, from model experimentation to high-availability production deployment.
• Develop evaluation frameworks and observability dashboards to monitor agent accuracy, latency, cost, and safety guardrails.
• Optimize agent performance by managing tool discovery and context window efficiency through standardized protocols.
• Embed healthcare regulatory compliance (e.g., HIPAA) directly into the platform layer through automated guardrails and audit trails.
• Implement security controls against prompt injection and ensure PII/PHI de-identification within agentic data flows.
• Provide subject matter expertise and technical support to engineering teams during implementation.
• Build prototypes, reference integrations, or proof-of-concept solutions to validate design decisions and de-risk complex implementations.
• Serve as a contributing member of Lirio’s Architecture Team, helping to maintain architectural coherence and platform quality.
• Diagnose and respond to issues in the implementation of agent orchestrations, adjusting guardrails and workflows as needed.

Qualifications

• 3–5+ years of experience in healthcare technology, with a deep understanding of clinical workflows, Electronic Health Record (EHR) integration (e.g., Epic, Cerner), and HL7/FHIR data standards.
• Bachelor's degree in related field preferred.
• Proven track record of building cloud-native autonomous agent systems in regulated environments.
• Extensive experience in LLMOps/MLOps, specifically managing the transition of agentic prototypes into production-grade healthcare applications.
• Hands-on experience with LLM APIs, AI coding tools (cursor, co-pilot, claude code, etc.) and orchestrations frameworks.
• Strong understanding of compliance requirements in regulated environments (HIPAA/HITRUST).
• Ability to design, implement, and maintain complex automation and agent workflows.
• Experience with security, audit, and risk mitigation in software delivery.
• Expert proficiency in Python (primary for AI) and C# or Java (for enterprise integration).
• Hands-on experience with Azure OpenAI Service, Azure AI Agent Service, and Azure Machine Learning (Azure ML).
• Proficiency with LangChain, Microsoft Semantic Kernel, and Databricks and/or Snowflake.
• Deep hands-on experience with emerging agent communication standards, specifically the Model Context Protocol (MCP).
• Advanced skills in Terraform for Infrastructure as Code (IaC), Docker, Kubernetes (AKS), and Azure DevOps (ADO) for CI/CD.
• Experience with Pinecone, Weaviate, or Azure AI Search for high-dimensional data retrieval.
• Prior work with Model Context Protocol (MCP) or similar integration standards.
• Demonstrated ability to lead platform adoption and drive organizational change.

Benefits

• Medical (HSA available)
• Dental
• Vision
• Short-term & long-term disability (company-paid)
• Life & AD&D (company-paid)
• 401K with company match
• 10 paid holidays, quarterly company closure dates, + holiday week company closure
• Flexible time off policy
• Work from home
• 6 weeks paid parental leave
• Salary range: $165k-$185k