AI Agent Developer

Corpay • Nashville, TN

1d • Onsite

About The Position

Corpay is seeking an experienced AI Agent Developer for its Corporate Payments division, specifically within the Account Payables line of business. This role is part of the Data & Analytics organization and AI Center of Excellence (AI CoE). The AI Agent Developer will be responsible for the end-to-end lifecycle of enterprise AI Agents, from design and development to deployment and continuous improvement, aiming to solve complex business and operational challenges within the Payables division. This position is crucial for enhancing Corpay's AI development capabilities and accelerating the implementation of AI solutions. The developer will leverage large language models (LLMs), agentic AI frameworks, enterprise data, APIs, and workflow automation to support various use cases. Beyond direct development, the role involves building AI capabilities across the organization by creating reusable patterns, standards, training materials, and providing hands-on education to enable functional teams to develop their own AI Agents. The ideal candidate possesses a strong blend of software and AI engineering skills with practical business acumen, is comfortable interacting with business stakeholders, can translate ambiguous problems into clear AI solutions, and can rapidly prototype while adhering to engineering, security, governance, evaluation, and operational standards for production deployment.

Requirements

• Bachelor’s degree in Computer Science, Information Systems, Artificial Intelligence, Data Science, Engineering, or a related field, or equivalent professional experience.
• 3+ years of relevant experience in AI application development, automation, machine learning, data engineering, software development, or a related technical discipline.
• Demonstrated hands-on experience building AI, LLM-powered, automation, or intelligent application solutions.
• Strong application-development skills using Python and experience working with REST APIs, JSON, SDKs, authentication mechanisms, and enterprise integrations.
• Experience working with one or more LLM platforms or APIs such as OpenAI, Azure OpenAI, Anthropic, Gemini, or comparable technologies.
• Understanding of LLM concepts including prompts, system instructions, tokens, context windows, structured outputs, tool/function calling, model selection, reasoning models, and model limitations.
• Experience designing or implementing Retrieval-Augmented Generation, embeddings, semantic search, document retrieval, vector search, or other enterprise knowledge-grounding solutions.
• Understanding of agentic AI concepts, including tool-enabled agents, multi-step workflows, context management, state, memory, validation, and human-in-the-loop patterns.
• Working knowledge of relational databases and SQL sufficient to enable AI applications to securely consume, investigate, and reason across structured enterprise data.
• Strong understanding of software engineering practices including modular design, debugging, testing, version control, Git, code review, deployment, and production support.
• Ability to systematically evaluate AI behavior using test cases, defined quality measures, regression testing, and repeatable evaluation methods.
• Understanding of common generative-AI risks and failure modes, including hallucination, prompt injection, data leakage, inappropriate tool usage, weak grounding, access-control failures, and unreliable outputs.
• Experience implementing or working with authentication, authorization, role-based access, security, privacy, logging, monitoring, and governance controls for enterprise applications.
• Strong analytical and problem-solving capability with the ability to break ambiguous business problems into structured, implementable solutions.
• Demonstrated ability to independently research, prototype, evaluate, and adopt rapidly evolving technologies.
• Strong communication skills with the ability to explain complex AI concepts, architecture, capabilities, risks, and limitations to both technical and non-technical audiences.
• Ability to work effectively with business stakeholders and cross-functional technology teams to move solutions from concept through production implementation.
• Ability and willingness to teach, coach, document, and transfer AI development knowledge to team members with varying levels of technical experience.

Nice To Haves

• Hands-on experience developing AI Agents using platforms or frameworks such as OpenAI Agents SDK, Microsoft Copilot Studio, Semantic Kernel, LangChain, LangGraph, AutoGen, or comparable technologies.
• Experience developing production-grade agentic workflows that combine LLM reasoning with enterprise data, business rules, APIs, tools, and automated actions.
• Experience with Microsoft Azure and related enterprise cloud technologies.
• Experience with Microsoft Fabric, Power BI, semantic models, enterprise data warehouses, or comparable analytics platforms.
• Experience working with vector databases, enterprise search, document-processing technologies, or knowledge-management platforms.
• Experience designing automated evaluation frameworks, LLM-as-judge approaches, golden datasets, regression testing, or AI quality scorecards.
• Familiarity with MCP and emerging standards for connecting AI Agents with enterprise tools, data, and services.
• Experience creating reusable AI development frameworks, templates, accelerators, or internal developer tooling.
• Experience delivering technical training, workshops, coaching, or enablement programs for developers, analysts, business technologists, or other AI practitioners.
• Experience supporting citizen-development or federated-development models in which centralized technical teams establish standards and enable distributed teams to build solutions safely.
• Experience building applications in B2B payments, accounts payable, fintech, financial services, or another highly regulated enterprise environment.
• Familiarity with Payables Operations or other high-volume operational environments where AI Agents can improve productivity, decision support, workflow execution, and service outcomes.

Responsibilities

• Designing, developing, testing, deploying, maintaining, and improving enterprise AI agents and LLM-powered applications for Payables business and operational needs.
• Partnering with business teams to understand processes, identify AI opportunities, gather requirements, and turn needs into technical solutions.
• Building AI agent workflows that can retrieve information, use data, call APIs and tools, complete tasks, and securely connect with company systems.
• Developing solutions using LLMs and enterprise AI platforms such as OpenAI/ChatGPT, Azure OpenAI, Copilot Studio, Microsoft Fabric, Claude, or similar tools.
• Building RAG solutions using company documents, databases, knowledge repositories, vector stores, and approved data sources.
• Connecting AI agents with company applications through APIs, databases, SDKs, MCP-compatible services, connectors, and other integration methods.
• Creating effective prompts, system instructions, context strategies, tool definitions, structured outputs, and multi-step agent workflows.
• Deciding when to use AI, business rules, traditional software, workflow automation, or human review within a process.
• Creating reusable AI components, templates, frameworks, connectors, testing methods, and development patterns.
• Establishing standards and repeatable practices that help AI solutions scale across Payables.
• Creating training materials, examples, documentation, and learning experiences for functional teams.
• Coaching and guiding Payables team members as they begin building AI agents for their own areas.
• Supporting teams in following architecture, security, evaluation, governance, and development standards while enabling safe self-service AI development.
• Reviewing and advising on agents built by functional teams to ensure they meet production-readiness and responsible-AI standards.
• Creating automated and human evaluation methods for measuring accuracy, relevance, completeness, task success, response time, cost, and user satisfaction.
• Developing test cases, golden datasets, regression tests, and other methods for consistently assessing agent behavior.
• Identifying and reducing AI risks such as hallucinations, incorrect tool use, incomplete retrieval, prompt injection, inappropriate actions, and data leakage.
• Implementing validation, grounding, guardrails, permissions, authentication, authorization, human review, and escalation processes based on risk.
• Protecting confidential company information and following Corpay security, privacy, governance, and responsible-AI standards.
• Optimizing AI solutions for performance, token use, response time, cost, reliability, scalability, and user experience.
• Testing new AI capabilities through proofs of concept and rapid prototypes to determine business value and production readiness.
• Applying engineering best practices when moving successful prototypes into production, including testing, version control, code review, documentation, deployment, monitoring, and support.
• Monitoring live AI agents through telemetry, user feedback, evaluation results, operational metrics, and business KPIs.
• Investigating AI-agent failures, finding root causes, and implementing fixes to improve reliability.
• Documenting AI architectures, prompts, workflows, data sources, integrations, dependencies, tools, evaluations, security considerations, and operating procedures.
• Collaborating with Data Engineering, Analytics, Software Engineering, Architecture, Information Security, Operations, and other teams to launch and support AI solutions.
• Explaining AI capabilities, limitations, risks, recommendations, and expected business value to technical and nontechnical stakeholders.
• Helping stakeholders identify which opportunities are best suited for AI versus traditional automation, analytics, software, or process improvement.
• Contributing to the AI Center of Excellence’s standards, methods, reusable assets, governance practices, and delivery approach.
• Staying current on new developments in generative AI, agentic AI, LLMs, multimodal models, evaluation, security, governance, and enterprise AI platforms.
• Evaluating new AI tools and approaches based on business value, reliability, security, scalability, maintainability, and production readiness.

Benefits

• Automatic enrollment into our 401k plan (subject to eligibility requirements)
• Virtual fitness classes offered company-wide
• Robust PTO offerings including: major holidays, vacation, sick, personal, & volunteer time
• Employee discounts with major providers (i.e. wireless, gym, car rental, etc.)
• Philanthropic support with both local and national organizations
• Fun culture with company-wide contests and prizes

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level