Principal Full-Stack AI Engineer

The Principal Full-Stack AI Engineer (Level V) is the most senior individual-contributor technical authority for AI-enabled software engineering within AssistRx Engineering. This is an enterprise software engineering role with deep AI responsibility, not a narrowly specialized machine learning role. The Principal Engineer defines technical strategy while remaining hands-on in the design and delivery of the company’s most complex systems.

The role spans conventional and AI-enabled architectures. Depending on the business problem, the Principal Engineer may lead a modern web application, REST and event-driven services, enterprise integrations, data workflows, cloud platforms, generative AI, predictive models, intelligent document processing, agentic automation, or a combination of these. The Principal Engineer is expected to choose technologies and languages based on the problem, and to recognize when conventional software or deterministic logic is a better solution than AI.

Reporting to the Vice President, Engineering, this role shapes enterprise technical direction, establishes reference architectures and engineering standards, advises executive and engineering leadership, represents AssistRx capabilities with clients, partners, and auditors, and develops the next generation of technical leaders. It is accountable for quality, security, reliability, performance, maintainability, cost efficiency, and the safe and compliant use of AI with protected health information across the enterprise.

Responsibilities

Enterprise Strategy And Architecture

• Define the multi-year technical strategy for AI-enabled software in partnership with Engineering, Product, and Architecture, aligning investments to business value, feasibility, risk, and total cost of ownership.
• Lead the architecture and delivery of the most complex enterprise-scale solutions spanning multiple products, clients, platforms, and technology stacks.
• Set the enterprise standard for when to use GenAI, predictive models, intelligent document processing, conventional application logic, workflow automation, or a hybrid approach.
• Own reference architectures and engineering standards for web applications, APIs, distributed services, integrations, data flows, model access, retrieval services, prompt and version management, evaluation, observability, security, and resilience.
• Identify emerging technologies and architectural patterns that create competitive advantage, and lead proofs of concept through production-scale adoption when evidence supports the investment.

Full-Stack Engineering And Delivery

• Remain hands-on in the design, implementation, review, troubleshooting, and production hardening of critical solutions across frontend, backend, cloud, integration, data, and AI layers.
• Ensure AI capabilities are embedded in coherent, usable, secure, and supportable applications rather than delivered as isolated model or service components.
• Lead the design of modern web experiences, REST APIs, event-driven and distributed services, enterprise integrations, identity and access patterns, and cloud infrastructure where required by the initiative.
• Resolve systemic technical constraints and cross-team dependencies, and create platform capabilities that allow multiple teams to deliver safely and consistently.
• Set standards for automated testing, CI/CD, infrastructure as code, observability, performance engineering, incident learning, and production readiness across AI-enabled solutions.

Applied AI And Responsible AI

• Architect enterprise LLM applications using retrieval-augmented generation, structured outputs, prompt design, function and tool calling, agent-based orchestration, and appropriate model-selection strategies.
• Set patterns for conversational AI, voice experiences, assistants, intelligent document workflows, and agentic systems, including state management, routing, human review, bounded autonomy, and safe fallbacks.
• Define enterprise evaluation standards for quality, grounding, safety, bias, privacy, latency, reliability, and cost; ensure regression testing and monitoring are integrated into the delivery lifecycle.
• Establish responsible AI practices appropriate for protected health information and high-impact healthcare workflows in partnership with Security, Compliance, Legal, and business owners.
• Set the standard for design documentation of AI features, covering intended behavior, context and retrieval design, prompt and…