AI Agent Developer, HR

Job Description We are Lennar  Lennar is one of the nation's leading homebuilders, dedicated to making an impact and creating an extraordinary experience for their Homeowners, Communities, and Associates by building quality homes and providing exceptional customer service, giving back to the communities in which we work and live in, and fostering a culture of opportunity and growth for our Associates throughout their career. Lennar has been recognized as a Fortune 500® company and consistently ranked among the top homebuilders in the United States.   A Career that Empowers You to Build Your Future The AI Agent Developer designs, builds, deploys, and maintains intelligent AI agents that transform how Lennar operates across our corporate functions. Embedded directly with the teams you serve, you will sit alongside Associates to learn their workflows firsthand, then translate what you see into production-grade agents that enhance productivity, streamline operations, and enable data-driven decision making. Working at the intersection of business strategy, AI engineering, and user experience, you will partner closely with product owners, engineers, and function leaders — and carry what you learn in the field back into Lennar's enterprise AI roadmap.   Your Responsibilities On The Team • Embed directly with corporate function teams: shadowing Associates, mapping how work actually gets done, and partnering with product owners, business analysts, and engineers to scope high-impact AI agent use cases. • Serve as an AI advisor to function leaders: presenting recommendations, framing trade-offs and risks in business terms, and building the confidence that moves teams from curiosity to committed adoption. • Design agent personas, roles, and workflows, including decision logic, triggers, escalation paths, and human-in-the-loop rules. • Build and configure AI agents using LLMs, retrieval-augmented frameworks, orchestration tools, and relevant APIs, integrating them with internal systems, data sources, and external services. • Develop robust prompt engineering strategies, tool invocations, memory and context management, and monitoring mechanisms so agents act effectively and reliably. • Deliver working prototypes and live demos early and often, using rapid feedback from business partners to shape each agent well before it reaches production. • Test, iterate, and validate agent behavior under real-world conditions through unit tests, scenario simulations, edge-case handling, and performance and safety monitoring. • Deploy agents into production environments and establish observability through logs, metrics, and usage dashboards, along with versioning, drift detection, and lifecycle management. • Maintain agents post-deployment by refining prompts, tuning models, and improving workflows, while championing adoption through Associate training, enablement materials, user guides, and change logs. • Ensure governance, compliance, security, and ethical considerations are built into agent design, including data access, audit trails, output safety, and escalation protocols. • Track and report the measures that prove value, hours returned, cycle time reduced, quality improved, and bring field learnings back to the enterprise as reusable patterns and best practices. Your Toolbox • Bachelor's degree in Computer Science, Engineering, Information Systems, Data Science, Business Analytics, AI, or a related technical field; advanced degree preferred. • 2–4+ years of experience in software engineering, AI/ML development, or automation, with at least one year working with LLMs and conversational AI. • Consultative mindset with genuine curiosity about how the business actually works, and the patience to sit with Associates until the real problem surfaces. • Excellent communication and presentation skills, with the ability to demo working solutions to non-technical audiences and translate complex business requirements into functional AI workflows. • Strong programming proficiency in Python and/or JavaScript/TypeScript, with demonstrated ability to build production-ready applications. • Proficient SQL skills for querying, transforming, and joining complex enterprise datasets across multiple systems. • Working understanding of AI agent concepts including LLMs, retrieval-augmented generation (RAG), prompt engineering best practices, and agent orchestration frameworks; familiarity with LangChain, LlamaIndex, function-calling patterns, Model Context Protocol (MCP), or multi-agent architectures is a plus. • Experience with cloud platforms, particularly AWS services such as Lambda, S3, and Bedrock, plus hands-on experience with Claude, Codex, GitHub, and Spotify Backstage; agentic coding tools such as Claude Code or Codex preferred. • Experience designing for production environments including scalability, reliability, monitoring, error handling, and performance optimization; MLOps practices such as model monitoring, drif