AI Engineer V (Principal)

Define and scale enterprise AI across the specialty medication access ecosystem as a senior individual-contributor technical authority.

Responsibilities

• Set the multi-year AI technical strategy and roadmap with the Vice President, Engineering, Product, and Architecture; align AI investments to business value, feasibility, and risk
• Lead architecture and delivery of complex enterprise AI/ML solutions, including generative AI, predictive models, and intelligent document processing across platforms, products, and clients
• Architect LLM applications using retrieval augmented generation, prompt engineering, structured outputs, and function and tool calling with agent-based orchestration
• Establish patterns for agentic workflows (task decomposition, tool/function calling, memory and state management, routing, boundaries, human review checkpoints, and fallback paths) for high-impact decisions such as benefits verification and prior authorization
• Identify new AI opportunities and emerging technologies; lead proofs of concept that move proven pilots to scale
• Choose the right approach per problem (prompting, retrieval augmentation, tools, task-specific models, or deterministic logic when models are not appropriate)
• Define standards for AI design documentation, including intended behavior, context and retrieval design, prompt and agent structure, evaluation approach, and fallback behavior
• Own the enterprise AI reference architecture, platform strategy, and engineering standards (model access, prompt/version management, retrieval services) and ensure adoption across engineering teams
• Lead evaluation of commercial models, AI platforms, and vendor tools; recommend build-versus-buy options to executives using quality, cost, security, strategic fit, and time-to-value
• Guide vendor and cloud provider relationships technically (model selection, capacity, pricing, and risk)
• Anticipate scaling, reliability, and cost challenges; direct architectural investments to address issues before client impact
• Set organization targets for accuracy, groundedness, hallucination rate, task completion, latency, and cost; guide model selection, tuning, and evaluation
• Define evaluation strategy, benchmark datasets, and automated test frameworks to measure output quality and detect regressions before release
• Improve retrieval pipelines via optimization of embeddings, chunking strategy, and inference performance to raise quality and reduce cost per transaction
• Direct error analysis and human-in-the-loop review with operations and clinical subject matter experts; ensure findings improve prompts, models, and guardrails
• Establish experimentation approach, including A/B testing across prompts, retrieval configurations, model selection, and workflow design
• Define quality gates and regression thresholds so AI features meet accuracy and safety requirements before release
• Set technical direction for pipelines preparing structured and unstructured healthcare data (enrollment forms, payer documents, clinical notes) for training, retrieval, and inference
• Partner with Data Engineering and Architecture on enterprise data contracts, feature sets, vector stores, and lineage for AI workloads
• Define enterprise standards for de-identification, masking, and data minimization when working with protected health information
• Define AI workload standards for CI/CD, source control, containerization, and infrastructure-as-code practices
• Establish versioning, promotion, and rollback practices for prompts, agents, and model configurations as versioned artifacts alongside application code
• Own the observability strategy for accuracy drift, groundedness, task completion, token consumption, latency, cost, and reliability, including alerting and incident response practices
• Own model and inference spend strategy using caching, routing, and model right-sizing
• Serve as final technical escalation for critical production issues and client-reported defects; drive systemic improvements to prevent recurrence
• Lead responsible AI approach and ensure compliance with healthcare privacy and security needs, including HIPAA and HITRUST
• Partner with Security, Compliance, and Legal on AI-specific risks (prompt injection, data leakage, insecure output handling) and confirm vendor agreements (including Business Associate Agreements) before PHI processing
• Define guardrails, content filtering, human oversight, and audit trails based on the risk profile of each use case
• Contribute to internal AI governance; represent AssistRx AI practices in audits, client due diligence, and security reviews
• Track emerging AI regulation and industry guidance; translate into engineering policy and practice
• Advise Vice President, Engineering and executive leadership on AI strategy, risk, investment, and capability
• Provide technical leadership across engineering teams by influencing enterprise architecture and engineering direction without direct authority
• Mentor Staff, Senior, and mid-level engineers; build the AI technical bench and increase AI fluency across the company
• Lead cross-functional technical initiatives and resolve complex technical disagreements across teams
• Work with Product Management, Client Services, and business leaders to identify high-value AI use cases and define success measures prior to build
• Communicate AI capabilities, limitations, risks, and results in plain language to technical and non-technical audiences, including executives, clients, and external partners
• Contribute to hiring strategy, interviewing, and role definition for AI and related engineering roles
• Advance AI-assisted and agentic development practices, including specification-driven workflows and agentic coding tools; share what works with engineering peers
• Participate in agile activities as needed (sprint reviews, retrospectives) and perform regular self-guided study

Requirements

• Bachelor’s degree in Computer Science, Engineering, Data Science, or related technical field (or equivalent experience); Master’s preferred
• 10+ years of software engineering experience, including 6+ years building and deploying AI or machine learning solutions in production
• Experience leading strategy and delivery of enterprise-scale AI used by real customers or operations teams, with significant measurable business outcomes
• Expert programming skills in Python, plus experience in .NET/C#/Java (or comparable enterprise language); backend services and REST APIs (e.g., FastAPI, Flask, ASP.NET)
• Hands-on expertise with large language models and generative AI patterns: retrieval augmented generation, prompt engineering, embeddings, vector/hybrid search, reranking, structured outputs, function/tool calling, context window management, and model evaluation
• Extensive experience architecting and operating production AI workloads on cloud AI/ML platforms (AWS preferred, including Amazon Bedrock and Amazon SageMaker; equivalent Azure experience acceptable via Azure AI Foundry, Azure OpenAI Service, or Azure Machine Learning)
• Expert knowledge of APIs, microservices, distributed systems, SQL, and modern practices including Git, CI/CD, containerization, and automated testing
• Ability to deliver in environments where privacy, security, and regulatory requirements shape solution design
• Demonstrated enterprise-level technical leadership: set technical strategy, drive architectural decisions across teams, and develop other technical leaders
• Ability to operate independently on highly ambiguous, high-impact problems; set direction and make sound tradeoffs with limited precedent
• Hands-on experience building with agentic coding tools (e.g., Claude Code, GitHub Copilot agents, Codex, Cursor), including specification-driven workflows and multi-step agent execution
• Practical understanding of production LLM behavior: hallucinations, prompt sensitivity, non-determinism, latency and cost tradeoffs
• Expertise in LLM evaluation methods: automated scoring, LLM-as-judge, and human review workflows
• Exceptional written and verbal communication to influence executives, clients, and engineers and represent the company’s AI approach externally

Preferred Qualifications

• Master’s or doctoral degree in Computer Science, Machine Learning, Data Science, or related field
• Experience in healthcare technology, specialty pharmacy, HUB services, ePA, or EHR/EMR integrations
• Experience with intelligent document processing, OCR, and extraction from unstructured enrollment or clinical documents
• Applied machine learning or data science background: experiment design, model evaluation, and error analysis
• Experience with Docker, Kubernetes, or infrastructure-as-code at scale
• Experience with agent and orchestration frameworks: LangChain, LangGraph, LlamaIndex, Semantic Kernel, Strands, or Model Context Protocol
• Experience with MLOps tooling, model registries, feature stores, and LLM observability or evaluation platforms
• Experience with model fine-tuning or smaller task-specific models for classification and extraction
• Familiarity with AI security guidance such as OWASP Top 10 for LLM Applications
• Familiarity with HIPAA, HITRUST, or responsible AI frameworks such as the NIST AI Risk Management Framework
• Prior experience establishing an AI function or serving as the senior AI technical leader for an organization
• Experience representing technical capabilities in client due diligence, security reviews, or external audits

Technologies

• Python; .NET; C#; Java; FastAPI; Flask; ASP.NET
• Retrieval augmented generation; prompt engineering; structured outputs; function and tool calling; agent-based orchestration
• Embeddings; vector search; hybrid search; reranking; context window management
• LLM-as-judge; AWS; Amazon Bedrock; Amazon SageMaker; Azure AI Foundry; Azure OpenAI Service; Azure Machine Learning
• APIs; microservices; distributed systems; SQL; Git; CI/CD; containerization; automated testing
• Claude Code; GitHub Copilot agents; Codex; Cursor

Location and Compensation

• Location: Florida (onsite)
• Salary: USD 162,239 - 204,048 per year

Competencies

• Technical Depth; Strategic Thinking; Analytical Rigor & Problem Solving
• Experimentation & Measurable Outcomes; Accuracy & Quality
• Sound Judgment & Risk Awareness; Ownership & Accountability
• Pragmatism & Bias for Delivery; Communication; Collaboration & Influence
• Technical Leadership & Talent Development; Curiosity & Learning Agility
• Adaptability; Initiative & Innovation; Ethics & Integrity