AI Engineer

Avalon Administrative Services LLC•Tampa, FL

13d•Remote

About The Position

The AI Engineer is a senior technical contributor responsible for leading the design, development, and deployment of scalable AI-powered solutions that support Avalon’s business objectives. This position owns complex AI features and projects from concept through production, including evaluating models and approaches, building reliable pipelines and integrations, and ensuring solutions meet high standards for accuracy, performance, and responsible use. While primarily focused on team objectives, the AI Engineer may also lead cross-functional AI initiatives, coordinating efforts, aligning timelines, and partnering with Product, Design, and Data teams to translate business challenges into practical, measurable AI applications. This position works closely with principal engineers and architects to help shape AI strategy and technical direction, contribute to architectural decisions, and ensure AI systems remain consistent, secure, maintainable, and scalable across the platform. The AI Engineer serves as a key contributor to expanding AI expertise across the organization by mentoring employees, supporting adoption of AI tools and practices, providing code and model reviews, and promoting best practices related to prompt and model evaluation, data quality, observability, and responsible deployment. This role combines hands-on technical execution with technical leadership and influence, helping advance Avalon’s AI capabilities while fostering a collaborative and innovative engineering culture. This position is eligible for remote work, but quarterly travel will be required to Avalon’s corporate office located in Tampa, Florida.

Requirements

Bachelor’s Degree in Management Information Systems, Computer Science, or related discipline; or the equivalent years of relevant business and technical experience.
A minimum of 8 to 10 years of experience in application software development and implementation, including hands-on experience building solutions with 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, and the judgment to choose the appropriate language for a given workload.
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 tooling).
Demonstrated expertise in prompt engineering and agentic engineering, including tool use, MCP, RAG, structured outputs, and techniques for reducing hallucination and improving reliability.
Experience mapping business workflows and building automations in n8n (preferred) or comparable workflow and orchestration platforms such as Make, Zapier, Temporal, or Apache Airflow.
Experience developing applications using Docker, AWS EC2, ECS/Fargate and Apache Kafka.
Experience with vector databases and embedding stores (such as pgvector, OpenSearch, or Pinecone).
Experience using standard interface/integration architecture and techniques (REST, webhooks, event-driven architecture, APIs, Microservices, SOA, SOAP/WSDL/XML, SAML).
Strong written and oral communication skills, including the ability to explain AI capabilities and limitations to non-technical stakeholders.
History of working in an Agile software development environment.
“Get stuff done” and flexible mindset for the greater good of the organization.
Proven success delivering high-quality solutions on time.
Excellent written and verbal communication skills, with the ability to clearly articulate complex technical concepts to diverse audiences, including engineers, product managers, and leadership.
Proven ability to collaborate effectively within a cross-functional team, while also influencing technical direction and decision-making within the team.
Demonstrates initiative and autonomy in identifying opportunities for improvement, driving solutions, and following through to execution.
Open to feedback and skilled at delivering constructive feedback to peers in a way that promotes growth, learning, and team cohesion.
Strong analytical and problem-solving skills, with the ability to navigate ambiguity and resolve complex technical challenges.
Consistently demonstrates ownership and accountability for delivering high-quality, maintainable, and scalable solutions.
Actively mentors junior and mid-level engineers, fostering a culture of inclusion, learning, and continuous improvement.
Comfortable stepping into informal leadership roles, such as guiding technical discussions or coordinating efforts on team-level initiatives.

Nice To Haves

Healthcare knowledge or experience preferred.
Experience self-hosting and administering n8n, including developing custom nodes and integrating n8n with AI agents and LLM services.
Experience building and evaluating RAG systems, embeddings, 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 working in an AWS or cloud-based environment, including managed AI services such as AWS Bedrock.
Integration of rules engines with AI-driven workflows.
Planning, developing, and deploying high-volume, mission-critical AI and software applications in a healthcare environment.
Knowledge or experience with HIPAA regulations and standards for security (PHI, IIHI), privacy, and transactions, particularly as they apply to the use of PHI with AI models and third-party AI vendors.

Responsibilities

Contribute to the design, technical direction, and architecture of AI-enabled solutions, collaborating with business and technical teams to build fit-for-purpose solutions that apply generative AI and agentic capabilities where they deliver measurable value.
Applies expert software engineering skills across a polyglot stack, including Python, Rust, Node.js/TypeScript, and Java, selecting the right language and runtime for each problem, and independently designs and develops key services with a focus on continuous integration and delivery.
Designs, builds, and operates agentic systems, including multi-step and multi-agent workflows, tool and function calling, Model Context Protocol (MCP) servers and integrations, retrieval-augmented generation (RAG) pipelines, and agent memory and orchestration patterns.
Applies advanced prompt engineering and context engineering practices, such as system prompt design, structured outputs, few-shot examples, prompt chaining, and prompt versioning, to produce reliable, accurate, and cost-effective model behavior.
Maps business processes and designs, builds, and maintains workflow automations using workflow orchestration platforms, with a strong preference for n8n, integrating AI agents with enterprise systems, APIs, and data sources.
Establishes evaluation, testing, and observability practices for AI systems, including evaluation suites, regression testing of prompts and agents, guardrails, tracing, and monitoring of output quality, latency, and token cost.
Participates in code reviews, including review of prompts, agent configurations, and workflow definitions, proactively identifying and mitigating potential issues and defects and assisting with continuous improvement.
Develops complex, modular, and reusable application code which utilizes SQL and vector data sources. Applies Enterprise Software Design Patterns as well as emerging AI design patterns, and builds reusable components such as prompt libraries, tool definitions, and workflow templates.
Drives continuous improvement efforts by identifying and championing practical means of reducing time to market while maintaining high quality, including evaluating and promoting AI-assisted development tools and practices across engineering teams.
Embrace industry best practices like continuous integration, continuous deployment, automated testing, TDD, and evaluation-driven development for AI components.
Follows agreed upon SDLC procedures to ensure that all information system products and services meet both explicit and implicit quality standards, end-user functional requirements, architectural standards, performance requirements, audit requirements, security rules, and responsible AI and data governance standards, and that external facing reporting is accurately represented.
Understands the strategic alignment of IT and AI solutions with business objectives; demonstrates a working knowledge of specific components of health plan operations and associated technical dependencies and identifies opportunities where AI and automation can improve them.
Responsible for the delivery of production-ready AI solutions that support the operations of the company, including clear documentation and knowledge transfer to the teams that will operate them.