AI Engineer - WFH
About the Company
Avalon Healthcare Solutions specializes in diagnostic intelligence, helping transform how diagnostic testing is managed across the healthcare ecosystem. Its proprietary Diagnostic Insights Platform combines evidence-based policies, curated laboratory networks, and real-time analytics to simplify diagnostic decisions, support innovation, and optimize healthcare investments. Avalon supports more than 30 health plans and 100 million members nationwide. Its solutions cover routine and genetic testing management, automated adherence, and end-to-end diagnostic support, helping reduce waste, improve clinical outcomes, and make healthcare more affordable. Avalon is an Equal Opportunity Employer, including veterans and individuals with disabilities.
About the Role
Avalon Healthcare Solutions is seeking an experienced AI Engineer to lead the design, development, and deployment of scalable AI-powered solutions that support business objectives. This senior technical contributor will take ownership of complex AI features from initial concept through production, evaluating models and technical approaches, building reliable pipelines and integrations, and ensuring solutions meet standards for accuracy, performance, security, and responsible use. The role focuses on generative AI, agentic systems, workflow automation, and enterprise software engineering. You will collaborate with Product, Design, Data, principal engineers, and architects to translate business needs into practical AI applications, contribute to architectural decisions, and support the development of consistent, secure, and maintainable systems. Alongside hands-on development, you will help strengthen AI capabilities across the organization through mentoring, code and model reviews, technical guidance, and the adoption of effective AI engineering practices.
Key Responsibilities
Contribute to the technical direction and architecture of AI-enabled solutions, identifying opportunities to apply generative AI and agentic capabilities to measurable business needs. Design, develop, and maintain application services using Python, Rust, Node.js/TypeScript, Java, and other suitable technologies. Build and operate agentic systems, including multi-step and multi-agent workflows, tool and function calling, Model Context Protocol (MCP) integrations, retrieval-augmented generation (RAG) pipelines, and agent memory and orchestration patterns. Apply advanced prompt and context engineering techniques, including system prompts, structured outputs, few-shot examples, prompt chaining, and prompt versioning. Map business processes and build workflow automations using orchestration platforms, preferably n8n, integrating AI agents with enterprise systems, APIs, and data sources. Establish evaluation and observability practices for AI systems, including evaluation suites, prompt and agent regression testing, guardrails, tracing, and monitoring of output quality, latency, and token costs. Participate in code reviews covering application code, prompts, agent configurations, and workflow definitions, identifying defects and opportunities for improvement. Develop modular, reusable application components that work with SQL and vector data sources, applying enterprise software design patterns and emerging AI design patterns. Create reusable prompt libraries, tool definitions, and workflow templates. Evaluate and promote AI-assisted development tools and practices that can reduce delivery time while maintaining quality. Apply continuous integration, continuous deployment, automated testing, test-driven development, and evaluation-driven development practices. Follow established software development lifecycle (SDLC) procedures and meet functional, architectural, performance, security, audit, quality, and responsible AI requirements. Identify opportunities to improve health plan operations through AI and automation, considering business objectives and related technical dependencies. Deliver production-ready AI solutions with clear documentation and knowledge transfer for teams responsible for ongoing operation. Mentor junior and mid-level engineers, contribute to technical discussions, and encourage continuous learning and improvement across engineering teams. Collaborate with cross-functional partners, communicate technical decisions clearly, and provide constructive feedback that supports team development.
Required Qualifications
Bachelor’s degree in Management Information Systems, Computer Science, or a related discipline, or equivalent relevant business and technical experience. Eight to ten years of experience in application software development and implementation, including hands-on development using large language models (LLMs), generative AI, and AI tooling. Strong proficiency in Python, Rust, GoLang, and Node.js/TypeScript, with working knowledge of Java and the JVM ecosystem. Hands-on experience with LLM APIs and SDKs such as Anthropic, OpenAI, Azure OpenAI, or AWS Bedrock, and agent frameworks such as LangChain/LangGraph, LlamaIndex, or comparable tools. Demonstrated expertise in prompt engineering and agentic engineering, including tool use, MCP, RAG, structured outputs, and techniques to reduce hallucinations and improve reliability. Experience mapping business workflows and building automations with n8n or comparable platforms such as Make, Zapier, Temporal, or Apache Airflow. Experience developing applications with Docker, AWS EC2, ECS/Fargate, and Apache Kafka. Experience with vector databases and embedding stores, such as pgvector, OpenSearch, or Pinecone. Knowledge of integration and interface architectures, including REST, webhooks, event-driven architecture, APIs, microservices, SOA, SOAP/WSDL/XML, and SAML. Experience working in an Agile software development environment. Strong written and verbal communication skills, including the ability to explain AI capabilities and limitations to non-technical stakeholders. Proven ability to deliver high-quality solutions on time, solve complex technical problems, and work effectively through ambiguity. Ability to collaborate across functions while influencing technical direction and decision-making. Demonstrated ownership, initiative, accountability, and commitment to building maintainable and scalable solutions. Willingness to accept feedback, provide constructive guidance to peers, and take on informal technical leadership responsibilities.
Preferred Qualifications
Healthcare industry knowledge or experience. Experience self-hosting and administering n8n, developing custom nodes, and integrating workflows with AI agents and LLM services. Experience building and evaluating RAG systems, embedding solutions, and model evaluation pipelines; familiarity with fine-tuning is a plus. Knowledge of AI security and safety practices, including guardrails, prompt injection mitigation, and responsible AI principles. Experience in AWS or other cloud-based environments, including managed AI services such as AWS Bedrock. Experience integrating rules engines with AI-driven workflows. Experience planning, developing, and deploying high-volume, mission-critical AI and software applications in healthcare. Knowledge of HIPAA requirements and security and privacy standards for protected health information (PHI), individually identifiable health information (IIHI), and healthcare transactions, particularly when using AI models and third-party AI vendors. Location and Work Arrangement This position is eligible for remote work. Quarterly travel to Avalon Healthcare Solutions’ corporate office in Tampa, Florida, is required.