Sr. AI Integration Engineer

Lightedge•Nashville, TN

About The Position

The Senior AI Integration Engineer plays a central role in building, integrating, deploying, and supporting AI-driven workflows across Lightedge’s core operational and business systems. This position is an execution partner to AI architecture leadership, helping translate agentic design concepts and approved business needs into production-ready AI agents, automations, and integrations that improve workflow execution, operational efficiency, and decision support. The ideal candidate combines strong software engineering and systems integration skills with practical experience delivering AI-enabled workflows in business environments. This person must be comfortable working directly with stakeholders to gather requirements, refine scope, and iterate quickly, while also owning a backlog of business-facing AI workflows and serving as the primary technical owner for those workflows once they move into production.

Requirements

Experience building and supporting production workflow integrations across enterprise systems such as ServiceNow, Salesforce, APIs, middleware, and related business platforms.
Experience taking prototypes, proofs of concept, or citizen-developed automations into governed production environments with appropriate controls, reliability, and supportability.
Experience supporting production applications, integrations, or automations with direct operational ownership responsibilities.
Working knowledge of security, access controls, logging, monitoring, and change-management practices for business-critical systems.
Strong proficiency in Python for AI integrations, workflow automation, and data processing.
Experience with one or more of JavaScript/TypeScript, Java, or C# for API and application development.
Experience building and supporting APIs, microservices, distributed systems, and CI/CD pipelines.
Experience translating business requirements into production-ready technical workflows and integrations.
Experience evaluating AI outputs, prompt behavior, workflow quality, and operational reliability before production release.
Experience deploying and supporting production systems in cloud environments such as AWS, Azure, or GCP.
Ability to work directly with stakeholders to gather requirements, define scope, and iterate based on feedback.
Excellent communication skills and ability to translate technical decisions into business impact.
Bachelor's degree in Computer Science, Engineering, Information Systems, or equivalent practical experience.
5+ years of relevant experience in software engineering, systems integration, workflow automation, or AI-enabled application delivery.

Nice To Haves

Experience integrating AI-enabled workflows into ServiceNow, Salesforce, or similar enterprise platforms.
Experience building LLM-based applications, agents, or workflow automations using frameworks such as LangChain, LlamaIndex, Semantic Kernel, or equivalent tools.
Experience developing AI-powered assistants, copilots, or intelligent automation workflows used by business teams.
Experience with prompt engineering, evaluation, and tuning of generative AI systems in production contexts.
Experience with Kubernetes and container-based deployment models.
Experience with MCP-style integration patterns, orchestration layers, or agent-accessible tool frameworks.
Experience with SQL and working with operational or analytics data across enterprise platforms.
Familiarity with vector databases, RAG pipelines, and workflow patterns that combine structured system context with LLM reasoning.
Familiarity with observability, support runbooks, and incident response practices for automation or integration services.
Experience with enterprise LLM platforms including ChatGPT, Claude, Gemini, Copilot, or similar tools.
Previous experience owning a backlog of automation or AI workflow enhancements for internal business users.

Responsibilities

AI Agent, Harness & Workflow Development: Design, develop, and maintain production-grade AI agents, harnesses, workflows, services, and integrations that support internal business processes and cross-functional execution.
AI Agent & Workflow Lifecycle Management: Own the end-to-end lifecycle of AI agents and AI-driven workflows, from intake and requirements shaping through production readiness, deployment, monitoring, support, periodic review, and continuous improvement.
Stakeholder Partnership: Work directly with internal teams to gather requirements, refine scope, collect feedback, and translate business needs into practical AI-enabled workflow solutions.
Owned Backlog: Maintain and execute a backlog of high-value business-facing AI workflows and automations that align with Lightedge priorities across operations, support, sales, and other internal functions.
System Integration: Build and support integrations across enterprise systems such as ServiceNow, Salesforce, portals, APIs, middleware, and other workflow platforms used by the business.
Production Ownership: Serve as the primary technical owner for AI workflows once they move from prototype into production, unless and until a deliberate transition to another long-term owner is defined.
Operational Support: Provide first-level support for production AI workflows that support critical business processes, including monitoring, issue triage, defect resolution, incident coordination, and early-life stabilization.
Controls and Readiness: Implement the controls required for safe production adoption, including testing, evaluation, observability, secrets handling, approval steps, rollback planning, and change-management alignment.
Engineering Standards: Contribute to codebases, deployment pipelines, support practices, and implementation standards for AI-enabled workflow delivery.
Optimization: Monitor, evaluate, and optimize the accuracy, reliability, cost, and business effectiveness of deployed AI workflows and integrations.
Documentation: Maintain clear technical documentation, workflow diagrams, runbooks, support notes, and production-readiness artifacts for delivered solutions.
Cross-Functional Collaboration: Partner with AI architecture, Security, Compliance, IT, Operations, and platform teams to ensure AI workflows are secure, supportable, and aligned with governance requirements.
Communications: Regularly communicate delivery status, risks, support needs, and business impact to stakeholders and leadership.
Architecture Contribution: Contribute implementation insight and field feedback into broader AI design and governance decisions, while not serving as the primary owner of enterprise AI strategy or architecture.