Sr AI Engineer

Arthrex•Pelican Bay, FL

23h

About The Position

Arthrex is a global medical device company and a leader in new product development and medical education in orthopedics. Arthrex is actively seeking a Sr AI Engineer. As a Senior AI Engineer, you'll play a key role within our Custom AI Development team, responsible for designing and implementing advanced AI solutions tailored to Arthrex specific use cases. You'll combine strong hands-on engineering with solid architectural thinking, helping drive innovation at the intersection of Large Language Models, retrieval architectures, agentic AI, and enterprise grade data integration. This role combines hands on engineering with meaningful technical ownership. You'll work closely with cross functional teams to deliver scalable GenAI solutions that create business value across Arthrex. While the main focus lies on internal solutions for Arthrex teams, this role also includes contributing to the development of digital products for external customers, including healthcare professionals. You'll be actively involved in initiatives such as Arthrex Intelligence and ARTI, our AI powered flagship applications, with a focus that goes beyond classic RAG into agentic retrieval, agent orchestration, tool usage, and autonomous multi agent architectures. Excellent communications and analytical skills, strong technical project management skills and a Bachelors’ degree will be essential for this position. Join our talented team at a global medical device company focused on Helping Surgeons Treat Their Patients Better™. Main Objective: AI Engineers design, develop, test, deploy and maintain Enterprise Grade AI solutions that meet business and customer needs. The focus is Custom AI Development for Arthrex specific use cases, meaning complex code first AI use cases that are too specific, too architecturally demanding, or too critical in terms of security and compliance to be implemented through Embedded AI or Hybrid AI approaches. The job family covers the full lifecycle from discovery and prototyping through production scaling, including Large Language Models, retrieval architectures, agentic AI, enterprise data integration, evaluation plus responsible AI. It also explicitly includes the engineering of composable AI frameworks and reusable API based capabilities that can be embedded into multiple applications and touchpoints across Arthrex.

Requirements

Experience developing software using Agile methodologies is preferred
Strong proficiency in Python and relevant AI and ML frameworks
Strong understanding of retrieval augmented generation, prompt engineering, embeddings, vector databases, and agent-based systems
Hands on experience with modern cloud native AI stacks and enterprise integration patterns
Experience building platform level AI capabilities, including orchestration layers, reusable components, standardized interfaces, and operational controls that support multiple AI solutions at scale
Strong communication skills and ability to work across organizational boundaries
At least 1 year of experience in one or more of the following areas, with willingness to grow across the broader AI engineering stack
Python development or similar modern programming languages
Prompt engineering and LLM application development
Basic retrieval workflows including document preparation, chunking, embeddings, and vector search concepts
Cloud native services and API based integration patterns
Willingness to learn the tools, languages, and frameworks required by the project
Hands on understanding of RAG concepts including retrieval configuration, grounding, semantic search, vector databases, and response quality improvement
Experience building and integrating AI services with enterprise data sources, APIs, and external tools
Familiarity with modern AI engineering workflows including testing, evaluation, logging, and deployment
Strong proficiency in Python and relevant AI and ML frameworks used for LLM applications and agent based systems
Strong understanding of classic and agentic RAG, prompt engineering, embeddings, vector databases, tool calling, and agent orchestration
Hands on experience with Azure OpenAI, Azure AI Search, Microsoft Foundry, and other cloud native AI services
Experience building intelligent systems that connect structured and unstructured enterprise data with AI models and external services
Experience defining and running AI evaluation processes for quality, grounding, reliability, and performance, preferably with MLflow or similar tooling
Understanding of emerging integration and communication patterns such as MCP and agent to agent concepts
Bachelor’s degree required
5+ years AI experience
2+ years GenAI relevant work experience required, including strong recent experience in GenAI, LLM based applications, or AI product development

Nice To Haves

Certifications in cloud, AI, or data technologies are a plus
Knowledge of Azure based AI services or comparable cloud native AI platforms is preferred
Nice to have experience with graph RAG, knowledge graphs, multimodal AI, Azure Document Intelligence, and voice based AI interaction patterns

Responsibilities

Design and develop custom AI applications using modern AI platforms and cloud native services
Build retrieval augmented generation solutions including classic and agentic patterns covering retrieval, orchestration, and reasoning approaches
Design and implement agentic AI architectures enabling autonomous decision making, tool invocation, and agent collaboration in enterprise contexts
Develop intelligent systems that connect AI models with structured and unstructured Arthrex data plus external tools and enterprise services
Build reusable AI capabilities and frameworks that can be consumed via APIs across multiple applications and touchpoints
Design for composability, reusability, and platform thinking, not only single solution delivery
Engineer production readiness including monitoring, incident readiness, and deployment discipline for AI services
Implement governance by design including security controls, compliance requirements, evaluation gates, and responsible AI practices
Collaborate with stakeholders such as product owners, business analysts, and subject matter experts to translate business problems into scalable AI solutions
Participate in code reviews, testing, documentation, and production support activities
Evaluate emerging GenAI technologies and frameworks to broaden Arthrex AI capabilities when needed
Adhere to the Quality System Procedure and Change Control
Support the development of well scoped AI components such as prompt variants, retrieval configuration, document preparation, chunking, metadata mapping, and simple tool integrations
Assist with connecting structured and unstructured data sources to AI workflows and retrieval pipelines
Implement smaller Python based services, utilities, and API integrations under guidance of more senior engineers
Contribute to testing, evaluation runs, documentation, and issue resolution for AI solutions in development and test environments
Help improve answer quality, grounding, and response consistency through iterative tuning of prompts, retrieval settings, and content preparation
Learn and apply established engineering patterns for RAG, agent based systems, cloud deployment, and responsible AI controls
Implement features end to end within a defined Custom AI use case, including Python services, retrieval configuration, prompt design, tool invocation, and data integration
Extend classic and agentic RAG workflows by improving retrieval logic, orchestration steps, citation behavior, and grounding quality
Build and maintain integrations with enterprise data, APIs, and external tools used by AI applications
Contribute to reusable AI components and internal frameworks that can be leveraged across multiple solutions
Participate in code reviews and collaborate actively with product owners, business analysts, and subject matter experts to translate requirements into technical implementation
Support operational readiness through logging, monitoring, troubleshooting, and controlled deployment activities
Design and implement advanced Custom AI solutions across the full lifecycle from architecture through deployment and production support
Lead the design of RAG and agentic AI architectures including retrieval strategy, orchestration patterns, tool usage, memory considerations, and agent collaboration
Contribute to architectural standards, reusable patterns, and best practices for scalable enterprise AI solutions
Design and build composable AI services and API based capabilities that can be embedded into multiple applications and touchpoints
Mentor lower level AI Engineers through technical guidance, code reviews, and design coaching
Drive AI evaluation practices for quality, grounding, reliability, and performance, including structured test datasets, benchmarking, and continuous improvement loops
Ensure solutions are engineered with security, compliance, responsible AI, and production readiness in mind