Lead, AI Engineer

Royal Caribbean Cruises Ltd•Miami, FL
•Onsite

About The Position

Royal Caribbean Group is seeking a Lead, AI Engineer for its AI & Analytics Team and GenAI Solutions Engineering team. The role sets engineering standards for generative AI across the company and leads projects spanning multiple brands and business functions. It works closely with the GenAI Center of Excellence, business users, engineering and data teams, platform and security teams, and product managers. The position is full-time, onsite in Miami, Florida, and reports to the Director, AI Engineering. It is not eligible for work authorization sponsorship. The Lead, AI Engineer establishes standards and shared tools for agentic coding, defines testing and evaluation practices for trustworthy production AI systems, and leads enterprise GenAI design and delivery. The role develops secure, production-ready applications and agents using Azure services and full-stack technologies; supports LLMOps, governance, and responsible AI; and mentors engineers through standards, reusable assets, and hands-on enablement.

Requirements

  • At least 7 years of professional software engineering experience, including at least 2 years building and shipping GenAI or LLM-based applications to production.
  • Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
  • Advanced daily hands-on proficiency with agentic coding tools such as Claude Code, including context engineering, instruction files, subagents, hooks, and parallel workflows, and sound judgment in reviewing and validating AI-generated code.
  • Demonstrated experience building skills, plugins, slash commands, subagents, or MCP servers adopted by other engineers and distributing them through a shared repository or catalog.
  • Experience defining and driving engineering standards across multiple teams or products, including reusable templates, shared tooling, and agent-readable guidance.
  • Strong Python skills and TypeScript or another full-stack language, with the ability to design sound APIs and architectures and direct AI agents toward maintainable results.
  • Hands-on expertise in unit, integration, contract, and end-to-end testing; test automation in CI; AI-assisted test generation and maintenance; and testing systems with non-deterministic components.
  • Experience designing and operating LLM evaluations, including golden datasets, metrics, LLM-as-judge and human review, release gates, and production quality monitoring.
  • Deep understanding of GenAI architectures, including RAG, tool use and function calling, MCP, and single- and multi-agent orchestration.
  • Proven expertise with Azure services, including Azure AI Foundry, Container Apps, AI Search, APIM, Key Vault, and Monitor, as well as containerization and infrastructure as code.
  • Experience with Azure DevOps or GitHub for CI/CD, release management, and environment promotion.
  • Experience with enterprise identity management, including Entra ID, OAuth 2.0, and service principals; secure coding; and responsible AI implementation, including secure use of AI coding tools with enterprise data.
  • Experience with observability and LLMOps, including tracing, prompt and model versioning, monitoring, and cost management.
  • Track record of partnering directly with business users to turn requirements into working prototypes, delivering cross-functional or enterprise-scale projects with multiple stakeholders, and mentoring engineers.
  • Strong problem-solving skills and ability to work effectively in a fast-paced, dynamic environment.
  • Strong written and verbal communication skills, including the ability to explain technical trade-offs and standards to engineers, business partners, and senior leadership.

Nice To Haves

  • Master's degree in Computer Science, Engineering, Data Science, or a related field.
  • Experience with the Claude Agent SDK or similar frameworks, and running coding agents headlessly in CI/CD for review, testing, or automation.
  • Experience operating an internal plugin or skills marketplace, including versioning, testing, and measuring adoption.
  • Experience with Databricks, including Unity Catalog, Genie, and MCP integrations, and enterprise semantic or data layers.
  • Familiarity with Microsoft Copilot Studio, Microsoft 365 Copilot extensibility, and Semantic Kernel.
  • Experience with evaluation and observability tooling for LLM applications and agents.
  • Experience with multi-cloud GenAI platforms such as AWS Bedrock or Google Vertex AI.
  • Experience with MCP server design and agent-to-agent interoperability patterns.
  • Experience with AI safety testing, including red teaming, prompt-injection testing, and adversarial evaluation.
  • Experience establishing or contributing to AI governance or an engineering community of practice in a large enterprise.

Responsibilities

  • Use agentic coding tools daily and establish enterprise practices for context engineering, instruction files, plan-then-implement workflows, subagents, parallel sessions, hooks, permissions, and sandbox settings.
  • Build and maintain shared skills, plugins, slash commands, subagents, hooks, and MCP servers, and distribute them through a versioned catalog.
  • Publish and maintain concise, tested, agent-readable engineering standards and guidance.
  • Define an AI-assisted delivery lifecycle with spec-driven development, reviewable changes, automated AI-assisted code review, human accountability, and safeguards for security, secrets, data classification, and intellectual property.
  • Establish agent-ready reference architectures, project templates, and reusable accelerators.
  • Measure the impact of AI-assisted engineering and use evidence to improve tools, prompts, and practices.
  • Partner with the GenAI Center of Excellence to publish standards, conduct design reviews, and retire outdated patterns.
  • Set testing strategies for GenAI systems, including unit, integration, contract, end-to-end, regression, load, and security testing.
  • Use coding agents to generate and maintain tests, with human-reviewed intent and checks such as mutation testing.
  • Build test harnesses for non-deterministic systems, including mocked model and tool responses, recorded fixtures, and deterministic seams around LLM calls.
  • Create verification loops for agents and enforce automated CI/CD quality gates for tests, analysis, scanning, AI-assisted review, and evaluations.
  • Lead blameless post-incident reviews and incorporate findings into standards, skills, and tests.
  • Design and own an enterprise evaluation framework for LLM applications and agents, including datasets, evaluation methods, human review, and quality, safety, latency, and cost metrics.
  • Develop evaluation methods for RAG, tool-using agents, and multi-agent workflows; integrate evaluations into CI/CD release gates and production monitoring.
  • Define and validate LLM-as-judge methods, calibrate them against human labels, check for bias, and guide teams in building representative evaluation datasets.
  • Govern model, prompt, and configuration changes through versioned, evidence-based evaluation.
  • Lead technical design and delivery of cross-brand and cross-functional GenAI initiatives, including cross-domain agents and shared data and knowledge services.
  • Work with business users to understand requirements and workflows, build prototypes, gather feedback, and iterate toward production-ready solutions.
  • Architect and develop GenAI applications and agents using Azure AI Foundry, Azure Container Apps, Azure AI Search, and Azure Databricks.
  • Build full-stack solutions using Python, FastAPI, Next.js, and PostgreSQL, and design agentic workflows using tool-use patterns and MCP.
  • Design and optimize RAG pipelines, including hybrid search, semantic ranking, and vector indexing with Azure AI Search.
  • Support and extend Microsoft Copilot Studio and Microsoft 365 Copilot solutions, and advise on low-code, configurable, or custom-engineered approaches.
  • Conduct feasibility studies and proofs of concept and turn successful work into supported production services.
  • Implement authentication and authorization using Microsoft Entra ID, MSAL, and service principals, and manage secrets with Azure Key Vault.
  • Manage APIs and microservices with Azure APIM and FastAPI.
  • Lead CI/CD and infrastructure automation using Azure DevOps and GitHub, including environment promotion, release management, and rollback strategy.
  • Apply LLMOps practices for prompt and model versioning, deprecation planning, tracing, observability, drift detection, and cost and token monitoring.
  • Implement AI safety guardrails, including content filtering, prompt-injection protection, and output validation, aligned with enterprise security, data classification, and responsible AI requirements.
  • Mentor and coach engineers on AI coding agents and raise standards for design, code quality, testing, and evaluation.
  • Run workshops, demos, and office hours to encourage adoption of shared skills and plugins.
  • Contribute to AI governance and communicate technical trade-offs, risks, and progress to engineering peers, product owners, and senior leadership.

Benefits

  • Competitive compensation and benefits package
  • Career development opportunities
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service