AI Engineer IV (Staff)

AssistRx, LLC is seeking a senior AI engineering leader to design, build, and deploy production-grade AI solutions within the specialty medication access ecosystem. In this Florida onsite role, you will set technical direction for high-risk, high-complexity AI systems, with an emphasis on quality, performance, cost efficiency, and safe, compliant use of AI with PHI.

Role summary

AI Engineer IV (Staff) will own the architecture and engineering standards for AI development across the organization. You will lead end-to-end delivery of complex multi-system AI and machine learning capabilities, including generative AI, predictive models, and intelligent document processing, while ensuring evaluation rigor, monitoring, and release quality gates are in place for real-world customer and operations workflows.

Responsibilities

• Lead design, build, and deployment of complex AI and machine learning solutions advancing the AI roadmap, including generative AI, predictive models, and intelligent document processing
• Architect LLM applications using retrieval augmented generation, prompt engineering, structured outputs, function and tool calling, and agent-based orchestration
• Design agentic workflows with task decomposition, tool/function calling, memory and state management, routing, clear boundaries, human review checkpoints, and fallback paths for high-impact decisions such as benefits verification and prior authorization
• Lead design of APIs, services, and integrations embedding AI into existing AssistRx platforms and client-facing workflows, resolving cross-team technical dependencies
• Translate ambiguous business and clinical workflow requirements into technical strategies, designs, and production releases, scaling proven pilots across products and clients
• Select the right technical approach per problem, including prompting, retrieval augmentation, tool use, task-specific models, or deterministic logic when models are not the right answer
• Author and review design documentation covering intended behavior, context and retrieval design, prompt and agent structure, evaluation approach, and fallback behavior
• Own AI reference architecture, reusable components, and engineering standards including model access, prompt and version management, and retrieval services, and drive adoption across engineering teams
• Evaluate commercial models, AI platforms, and vendor tools, providing build-versus-buy guidance to the Vice President, Engineering based on quality, cost, security, and time to value
• Shape the AI technical roadmap with Product and Architecture, prioritizing by business value, feasibility, and risk, while maintaining the AI use case inventory and technical backlog
• Identify AI platform gaps and technical debt, and lead investments to close them
• Select, tune, and evaluate models against targets for accuracy, groundedness, hallucination rate, task completion, latency, and cost
• Define evaluation frameworks, benchmark datasets, and automated test suites to measure output quality and detect regressions before each release
• Optimize retrieval pipelines, embeddings, chunking strategies, and inference performance to improve quality and reduce cost per transaction
• Lead error analysis and human-in-the-loop review cycles with operations and clinical subject matter experts, applying findings to prompts, models, and guardrails
• Design and run structured experiments and A/B tests across prompts, retrieval configurations, model selection, and workflow design, using results to drive iteration
• Establish and enforce quality gates and regression thresholds so AI features meet defined accuracy and safety criteria before release
• Define pipelines that prepare structured and unstructured healthcare data (enrollment forms, payer documents, clinical notes) for training, retrieval, and inference
• Partner with Data Engineering on data contracts, feature sets, vector stores, and lineage for AI workloads
• Set standards for de-identification, masking, and data minimization when working with PHI
• Set standards for CI/CD, source control, containerization, and infrastructure-as-code practices for AI workloads
• Maintain versioning, promotion, and rollback practices for prompts, agents, and model configurations as versioned artifacts alongside application code
• Define monitoring for accuracy drift, groundedness, task completion, token consumption, latency, cost, and reliability via logging, observability, and alerting
• Track and manage model and inference spend, applying caching, routing, and model right-sizing to keep solutions cost-effective at scale
• Serve as escalation point for complex production issues and client-reported defects in AI-enabled features, leading root cause analysis and continuous improvement
• Build solutions that satisfy healthcare privacy, data security, and regulatory requirements including HIPAA and HITRUST
• Partner with Security and Compliance on AI-specific risks (prompt injection, data leakage, insecure output handling) and confirm vendor agreements including Business Associate Agreements are in place before PHI is processed
• Define guardrails, content filtering, human oversight, and audit trails appropriate to each use case’s risk profile
• Document model design, data sources, intended use, and known limitations to support internal AI governance, audits, and client due diligence
• Provide technical leadership across multiple teams without direct authority, influencing design decisions and engineering direction
• Mentor and coach senior and mid-level engineers on AI development, code quality, evaluation, and design practices, raising AI fluency across engineering
• Lead design reviews and peer code reviews, contributing to shared standards and reference architectures
• Work with Product Management and business stakeholders to identify high-value AI use cases and define success measures before build begins
• Communicate AI capabilities, limitations, risks, and results to technical and non-technical audiences, including engineering leadership, executives, and clients
• Participate in day-to-day agile activities including sprint planning, daily standups, sprint reviews, and retrospectives
• Apply and help improve AI-assisted and agentic development practices, including specification-driven workflows and agentic coding tools, and share what works
• Conduct self-guided study to stay current in the AI landscape and bring relevant techniques and tooling to the team

Required qualifications

• Bachelor’s degree in Computer Science, Engineering, Data Science, or related technical field (or equivalent experience)
• 7+ years of software engineering experience, including 4+ years building and deploying AI or machine learning solutions in production
• Track record of leading and shipping multiple AI features used by real customers or operations teams, with measurable business outcomes
• Strong programming skills in Python, plus experience in .NET/C#/Java or a comparable enterprise language, building backend services and REST APIs (for example FastAPI, Flask, or ASP.NET)
• Hands-on experience with large language models and generative AI patterns including retrieval augmented generation, prompt engineering, embeddings, vector and hybrid search, reranking, structured outputs, function and tool calling, context window management, and model evaluation
• Experience designing and deploying production AI workloads on cloud AI/ML platforms, with AWS preferred (Amazon Bedrock, Amazon SageMaker) or equivalent Azure experience (Azure AI Foundry, Azure OpenAI Service, Azure Machine Learning)
• Strong knowledge of APIs, microservices, SQL, and modern development practices including Git, CI/CD, containerization, and automated testing
• Ability to deliver in an environment where data privacy and security requirements shape solution design
• Demonstrated technical leadership across teams, including setting technical direction, driving architectural decisions, and mentoring engineers
• Ability to work independently on ambiguous, high-impact problems, set direction on technical approach, and make sound tradeoffs with limited precedent
• Hands-on experience building software with agentic coding tools such as Claude Code, GitHub Copilot agents, Codex, or Cursor, including specification-driven workflows and multi-step agent execution
• Practical understanding of how LLMs behave in production, including hallucination, prompt sensitivity, non-determinism, and latency and cost tradeoffs
• Strong knowledge of evaluation methods for LLM systems, including automated scoring, LLM-as-judge techniques, and human review workflows
• Excellent written and verbal communication skills for collaboration with engineers, executives, and clients in a fast-paced agile environment

Technologies

• Python, .NET, C#, Java
• FastAPI, Flask, ASP.NET
• Retrieval augmented generation, prompt engineering, embeddings
• Vector search, hybrid search, reranking, structured outputs
• Function calling, tool calling, context window management, model evaluation
• AWS, Amazon Bedrock, Amazon SageMaker; Azure AI Foundry, Azure OpenAI Service, Azure Machine Learning
• APIs, microservices, SQL
• Git, CI/CD, containerization, automated testing
• Claude Code, GitHub Copilot agents, Codex, Cursor
• A/B tests
• HIPAA, HITRUST

Preferred qualifications

• Master’s 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 data extraction from unstructured enrollment or clinical documents
• Applied machine learning or data science background, including experiment design, model evaluation, and error analysis
• Experience with Docker, Kubernetes, or infrastructure-as-code
• Experience with agent and orchestration frameworks such as 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 the OWASP Top 10 for LLM Applications
• Familiarity with HIPAA, HITRUST, or responsible AI frameworks such as the NIST AI Risk Management Framework
• Prior experience as an early or lead AI engineer helping an organization adopt AI

Pay range

USD 135,051 - 168,814 per yearly

Location: Florida (onsite)

Education: Bachelor’s degree in Computer Science, Engineering, Data Science, or related technical field (or equivalent experience)