Lead AI Engineer

Journey with us! Combine your career goals and sense of adventure by joining our exciting team of employees. Royal Caribbean Group is pleased to offer a competitive compensation and benefits package, and excellent career development opportunities, each offering unique ways to explore the world.

We are proud to be the vacation-industry leader with global brands — including Royal Caribbean International, Celebrity Cruises and Silversea Cruises — the most innovative fleet and private destinations, and the best people. Together, we are dedicated to turning the vacation of a lifetime into a lifetime of vacations for our guests.

TheRoyalCaribbeanGroup’s 

AI & Analytics Team has an exciting career opportunity for a full time Lead, AI Engineerreporting to the Director, AI Engineering.

The position is onsite and based in Miami, Florida.

The position is also not eligible for work authorization sponsorship.

Position Summary:

We are seeking a Lead, AI Engineer to set engineering standards for Gen AI across Royal Caribbean Group and to lead delivery of projects that span multiple brands and business functions. You will join the GenAI Solutions Engineering team within AI & Analytics and work closely with the GenAI Center of Excellence (CoE). You will also collaborate closely with business users to understand their requirements and quickly build prototypes they can react to.

You will be a power user of agentic coding tools such as Claude Code, and you will turn that fluency into shared skills, plugins, and standards that make every engineer and agent on the team faster and more reliable. You will define the testing and evaluation practices that keep Gen AI applications and agents trustworthy in production, then prove those practices on enterprise-wide initiatives by working with business stakeholders, data engineers, data scientists, platform and security teams, and product managers.

Essential Duties and Responsibilities

AI-Enabled Engineering & Standards

• Be a daily, advanced user of agentic coding tools (Claude Code, GitHub Copilot, Cursor, and similar) and set enterprise practices for them: context engineering, project instruction files (CLAUDE.md / AGENTS.md), plan-then-implement workflows, subagents, parallel sessions, hooks, and permission and sandbox settings.
• Design, build, and maintain skills, plugins, slash commands, subagents, hooks, and MCP servers that encode our standards and workflows (for example scaffolding, ticket creation, PR review, test and eval generation), and distribute them to engineers through a versioned, shared plugin catalog.
• Publish engineering standards as living, agent-readable instructions that both people and coding agents follow, and keep them short, tested, and current as tools and models change.
• Define an AI-assisted delivery lifecycle: spec-driven development, small reviewable changes, automated AI-assisted code review, and clear human accountability for everything that ships, with guardrails for security, secrets, data classification, and IP.
• Establish reference architectures, project templates, and reusable accelerators that are agent-ready, so teams across brands and functions start from a secure, tested, production-ready baseline.
• Measure the impact of AI-assisted engineering (cycle time, rework, defect rates, token cost) and use the evidence to refine tools, prompts, and practices.
• Partner with the GenAI CoE to publish standards, run design reviews, and retire patterns that no longer serve the enterprise.

Testing & Quality Engineering

• Set the testing strategy for Gen AI systems, including unit, integration, contract, end-to-end, regression, load, and security testing for APIs, retrieval pipelines, agents, and tool integrations.
• Use coding agents to generate and maintain tests at scale, with human-reviewed intent and checks such as mutation testing to confirm the tests actually catch defects.
• Build test harnesses that handle non-deterministic behavior, including mocked model and tool responses, recorded fixtures, and deterministic seams around LLM calls.
• Build verification loops that let agents check their own work (tests, type checks, linters, and evals) before a human reviews it.
• Enforce automated quality gates in CI/CD (tests, static analysis, dependency and secret scanning, AI-assisted review, and evaluation checks) so no agent or application ships without passing them.
• Lead blameless post-incident reviews and feed findings back into standards, skills, and tests.

Evaluation Frameworks

• Design and own the enterprise evaluation framework for LLM applications and agents: golden datasets, rubric- and model-graded evals, human review workflows, and task-completion, groundedness, hallucination, safety, latency, and cost metrics.
• Create evaluation approaches specific to RAG (retrieval precision and recall, citation accuracy), tool-using agents (tool selection, argument correctness, trajectory quality), and multi-agent workflows.
• Integrate evals into CI/CD as release gates and into production as continuous monitoring, with clear thresholds, dashboards, and regression alerts.
• Define and validate LLM-as-judge methods, including calibration against human labels and bias checks, and guide teams on building representative evaluation datasets.
• Govern model, prompt, and configuration changes through versioned, evidence-based evaluation before promotion.

Enterprise-Wide Delivery & Architecture

• Lead technical design and delivery of Gen AI initiatives that span multiple brands, business functions, and data domains, including cross-domain agents and shared enterprise data and knowledge services.
• Collaborate closely with business users to understand their needs, requirements, and workflows, and rapidly build working prototypes (using AI coding tools) that users can test and give feedback on, then iterate with them toward production-ready solutions.
• Architect and develop Gen AI 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 with tool-use patterns and the Model Context Protocol (MCP) to connect agents to enterprise APIs, data platforms, and third-party services.
• 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 when a low-code, configurable, or custom-engineered approach is the right fit.
• Conduct feasibility studies and proofs of concept, and turn successful ones into supported, production-grade services.

Platform, Security & LLMOps

• Implement secure 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 with Azure DevOps and GitHub, including environment promotion, release management, and rollback strategy.
• Apply LLMOps practices: prompt and model versioning, deprecation planning, tracing and observability, drift detection, and cost and token monitoring using Azure Monitor and Log Analytics.
• Implement AI safety guardrails, including content filtering, prompt injection protection, and output validation, in line with enterprise security, data classification, and responsible AI requirements.

Leadership, Governance & Collaboration

• Mentor and coach engineers across teams on working effectively with AI coding agents, and raise the bar for design, code quality, testing, and evaluation practice.
• Run hands-on enablement (workshops, demos, office hours) so skills and plugins are adopted, not just published.
• Contribute to the AI governance framework so that solutions align with enterprise AI principles, compliance requirements, and responsible AI practices.
• Communicate technical trade-offs, risks, and progress clearly to engineering peers, product owners, and senior leadership.

Qualifications:

• 7+ years of professional software engineering experience, with 2+ years building and shipping Gen AI 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 the judgment to review and validate AI-generated code.
• Demonstrated experience building skills, plugins, slash commands, subagents, or MCP servers that other engineers adopt, 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 (required) and TypeScript or another full-stack language, with the fundamentals to design sound APIs and architectures and to direct AI agents toward maintainable results.
• Hands-on testing expertise: unit, integration, contract, and end-to-end testing (for example pytest), test automation in CI, using AI to generate and maintain tests, and testing systems with non-deterministic components.
• Proven experience designing and operating LLM evaluation: building golden datasets, defining metrics, using LLM-as-judge and human review, and using evals to gate releases and monitor production quality.
• Deep understanding of Gen AI architectures, including RAG, tool use and function calling, MCP, and single- and multi-agent orchestration.
• Proven expertise with Azure cloud services, including Azure AI Foundry, Container Apps, AI Search, APIM, Key Vault, and Monitor, plus containerization and infrastructure as code.
• Experience with Azure DevOps or GitHub for CI/CD, release management, and environment promotion.
• Experience with enterprise identity management (Entra ID, OAuth 2.0, service principals), secure coding practices, and responsible AI implementation, including secure use of AI coding tools with enterprise data.
• Experience with observability and LLMOps: tracing, prompt and model versioning, monitoring, and cost management.
• Track record of partnering directly with business users to translate requirements into working prototypes, delivering cross-functional or enterprise-scale projects with multiple stakeholders, and mentoring other engineers.
• Excellent problem-solving skills and the ability to work effectively in a fast-paced, dynamic environment.
• Strong written and verbal communication skills, with the ability to explain technical trade-offs and standards to engineers, business partners, and senior leadership.
  
  Preferred Qualifications
• 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 (Unity Catalog, Genie, 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 Gen AI platforms (AWS Bedrock, Google Vertex AI).
• Experience with MCP server design and agent-to-agent interoperability patterns.
• Experience with AI safety testing, such as red teaming, prompt injection testing, and adversarial evaluation.
• Experience establishing or contributing to an AI governance or engineering community of practice in a large enterprise.

We know there's a lot to consider. As you go through the application process, our recruiters will be glad to provide guidance, and more relevant details to answer any additional questions. Thank you again for your interest in Royal Caribbean Group. We'll hope to see you onboard soon!

It is the policy of the Company to ensure equal employment and promotion opportunity to qualified candidates without discrimination or harassment on the basis of race, color, religion, sex, age, national origin, disability, sexual orientation, sexuality, gender identity or expression, marital status, or any other characteristic protected by law. Royal Caribbean Group and each of its subsidiaries prohibit and will not tolerate discrimination or harassment.