AI Agent Developer

Lennar•Bentonville, AR

About The Position

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 We are seeking a skilled and proactive Agent Builder to design, develop, deploy, and maintain intelligent AI agents that transform how we operate across our corporate functions. Working at the intersection of business strategy, AI engineering, and user experience, you'll translate complex business processes into production-grade agents that enhance associate productivity, streamline operations, and enable data-driven decision making. This role offers the unique opportunity to drive enterprise AI adoption while working with cutting-edge technologies in a collaborative, innovative-driven environment.

Requirements

Bachelor’s degree in Computer Science, Engineering, Information Systems, Industrial Engineering, Data Science, Business Analytics in AI or AI, or related technical field; advanced degree preferred.
2-4+ years of experience in software engineering, AI/ML development, or automation, with at least 1 year working with LLMs and conversational AI.
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.
Understanding of AI agent concepts including LLMs, retrieval-augmented generation (RAG), prompt engineering best practices, and agent orchestration frameworks.
Experience with cloud platforms, particularly AWS services (Lambda, S3, Bedrock) or similar cloud infrastructure.
Hands-on experience with Palantir Foundry or demonstrated ability to quickly learn enterprise data platforms.
Proven ability to integrate disparate systems through APIs, webhooks, and data pipelines
Experience designing for production environments: scalability, reliability, monitoring, error-handling, and performance optimization.
Strong problem-solving mindset with the ability to translate complex business requirements into functional AI workflows.
Excellent communication skills to collaborate with non-technical stakeholders and present technical concepts clearly.

Nice To Haves

Direct experience building and deploying AI agents within Palantir Foundry (Code Workspaces, AIP SDK, AIP Actions).
Familiarity with advanced agent frameworks and tools: LangChain, LlamaIndex, OpenAI function calling patterns, or similar.
Experience with Model Context Protocol (MCP) or other emerging standards for AI tool integration.
Knowledge of multi-agent orchestration and persona-based agent architectures.
Familiarity with enterprise business systems (ERP, CRM, HRIS) and workflow automation across corporate functions.
Experience with AWS Bedrock for deploying and managing foundation models.
Background in MLOps practices including model monitoring, drift detection, and A/B testing.
Understanding of responsible AI principles and experience implementing safety guardrails.

Responsibilities

Collaborate with stakeholders (product owners, business analysts, and engineers) to identify use cases for AI agent development and automation opportunities.
Contribute to the design of agent personas/roles, workflows, including decision logic, triggers, and escalation paths/human-in-the-loop rules.
Build and configure AI agents using LLMs, retrieval-augmented frameworks, orchestration tools and relevant APIs; ensure their integration with internal systems, data sources, and external services.
Develop robust prompt engineering strategies, tool invocations, memory/context management, and monitoring mechanisms for agents to act effectively and reliably.
Test, iterate and validate agent behavior under real-world conditions: unit tests, scenario simulations, edge-case handling, performance and safety monitoring.
Deploy agents into production environments, set up monitoring/observability (logs, metrics, usage dashboards), handle versioning, drift detection, and lifecycle management.
Maintain agents' post-deployment: identify improvements, retrain or fine-tune models or prompts, refine workflows, manage feedback/human-in-loop interventions.
Ensure governance, compliance, security and ethical considerations are baked into agent design (data access, audit trails, output safety, escalation protocols).
Document agent specifications, workflow diagrams, user guides, change logs, and training materials for internal teams.
Stay current with the rapidly evolving AI/agent space (LLMs, multi-agent orchestration, emerging standards, frameworks) and bring best practices into the organization.

Benefits

robust health insurance plans, including Medical, Dental, and Vision coverage
401(k) Retirement Plan, complete with a $1 for $1 Company Match up to 5%
Paid Parental Leave
Associate Assistance Plan
Education Assistance Program
up to $30,000 in Adoption Assistance
up to three weeks of vacation annually, alongside generous Holiday, Sick Leave, and Personal Day policies
New Hire Referral Bonus Program
significant Home Purchase Discounts
Everyone’s Included Day