Principal AI Engineer

Overview As a Principal AI Engineer at MRO, you will own the technical vision and implementation of AI capabilities that power our healthcare software products. You will design and build production AI systems — RAG pipelines, LLM integrations, human-in-the-loop workflows, and model quality frameworks — while setting the engineering standards other teams build against.  This is a hands-on technical leadership role. You will work closely with architecture, product, data engineering, and engineering teams to translate complex healthcare workflows into scalable, accurate, and compliant AI solutions. You bring deep AI/ML engineering experience, know how HIPAA applies to the systems you build, and have owned AI product quality end-to-end — not just contributed to it.  Responsibilities Prodigy Product AI Vision & Technical Ownership   Own the end-to-end technical vision for MRO Prodigy's AI layer — a production system that uses RAG, generative AI, and structured data reasoning to automate answers to Healthcare Registry questionnaires.  Define the AI roadmap for Prodigy, balancing near-term customer commitments against foundational capability investments that scale the product to enterprise maturity.  Evaluate and make build/buy/integrate decisions for AI capabilities — foundation model selection, embedding strategies, retrieval architectures, and orchestration frameworks — and own the consequences of those decisions.  Serve as the technical authority on all AI design decisions for Prodigy; produce architecture decision records, set standards, and ensure the architecture is defensible, auditable, and extensible.  AI/ML Solution Architecture & Implementation   Architect and evolve Prodigy's multi-modal retrieval pipeline, combining unstructured clinical document ingestion with structured EHR/FHIR data to surface accurate, citation-backed answers to registry questionnaire items.  Design and refine the answer generation layer — prompt engineering, context construction, grounding strategies, and output formatting — ensuring generated answers are clinically accurate and audit-ready.  Own the question routing and data source classification logic that maps registry questions to the right retrieval path, structured data field, or generation strategy.  Build and maintain the answer validation and confidence scoring framework, defining the statistics and quality thresholds that govern when answers are auto-accepted versus routed for human review.  Human-in-the-Loop & Model Improvement   Stay hands-on and close to the work: run direct ideation and feedback loops with Prodigy's end users (abstractors, registry, and quality teams) and with production analytics and monitoring systems — turning real usage signals into prioritized improvements that demonstrably move value, not just model metrics.  Evolve the feedback loop architecture that captures human corrections and routes them into continuous model improvement — ensuring Prodigy gets measurably better with every customer interaction.  Define the evals framework for Prodigy: how accuracy is measured, how regression is detected, and what signals trigger retraining or prompt revision.  Establish guardrails for hallucination detection and factual grounding specific to clinical registry use cases, where answer accuracy has direct downstream compliance implications.  Cloud & Data Architecture   Architect AI infrastructure across GCP (Vertex AI, BigQuery, Dataflow) and AWS (Bedrock), ensuring the pipeline is scalable, cost-efficient, and operationally observable.  Collaborate with data engineering to maintain high-quality, well-governed clinical and FHIR data inputs; define feature engineering and chunking strategies that optimize retrieval precision.  Define MLOps standards for Prodigy: model versioning, deployment gates, rollback procedures, drift monitoring, and audit trail requirements consistent with HIPAA compliance.  Technical Leadership & Enablement   Act as the AI technical mentor for the Prodigy squad and adjacent engineering teams — guiding developers on RAG patterns, LLM integration, responsible AI practices, and clinical data handling.  Collaborate with Security and Compliance to ensure Prodigy's AI layer meets HIPAA requirements, including PHI handling in prompts, data residency, and model audit logging.  Foster AI literacy across the broader engineering organization, helping teams understand when and how to apply AI safely in a regulated healthcare context.  Partner with Product Management to translate registry workflow complexity and customer feedback into technically sound AI capability improvements.  Qualifications Education & Background   Bachelor's in Computer Science, AI/ML, or related field; Master's or PhD preferred — or equivalent depth proven through shipped AI systems.  Strong ML / data science / statistics theory foundation with the ability to read research, assess applicability, and execute.  LLM Engineering & RAG   Hands-on LLM integration: prompt engineering, grounding, citation, hallucination mitigation, and output validation at clinical accuracy standards.  Experience with LangChain, LlamaIndex, or equivalent orchestration frameworks.  Built confidence scoring and auto-acceptance thresholds that govern when answers route to human review.  Designed human-in-the-loop feedback systems that capture corrections and feed them back into model improvement.  Production experience building RAG pipelines — document ingestion, chunking, embedding model selection, vector store management, and retrieval evaluation.  AI/ML Engineering & MLOps   Full ML lifecycle ownership in production: versioning, deployment gates, drift monitoring, rollback, and audit trails.  Strong Python and software engineering fundamentals — CI/CD, testing, code review.  Hands-on with vector databases (pgvector, Pinecone, Weaviate, or equivalent) and hybrid search.  Built evals framewo