The Senior AI Agentic Engineer is a hands-on software engineer responsible for designing, building, deploying, and supporting production-grade AI agents and intelligent automation solutions within the Truist Agentic Enterprise (TAE).
This role combines strong software engineering fundamentals with expertise in modern AI technologies, including large language models (LLMs), agent frameworks, orchestration patterns, retrieval systems, and enterprise integrations.
The engineer develops scalable, secure, and reliable solutions that combine AI capabilities, business logic, APIs, data services, and workflow automation to solve real business problems.
Working as a senior individual contributor, the role independently delivers well-defined initiatives, contributes to engineering standards and code quality, and helps increase team delivery velocity through technical leadership, code reviews, and reusable implementation patterns.
The ideal candidate brings deep Python expertise, strong engineering discipline, experience building AI-enabled applications, and a commitment to delivering enterprise-ready solutions that are observable, testable, maintainable, and governed.
ESSENTIAL DUTIES AND RESPONSIBILITIESFollowing is a summary of the essential functions for this job. Other duties may be performed, both major and minor, which are not mentioned below. Specific activities may change from time to time.
- Design, develop, deploy, and support production-ready AI agents, agentic workflows, and intelligent automation solutions.
- Build solutions that leverage LLMs, orchestration frameworks, retrieval systems, APIs, business services, and enterprise data sources to deliver measurable business value.
- Implement agent workflows using established engineering patterns, including tool orchestration, workflow routing, human-in-the-loop controls, session management, and safe fallback mechanisms.
- Develop and maintain integrations with enterprise applications, services, APIs, and governed data platforms.
- Design and optimize prompts, tool definitions, retrieval strategies, context management approaches, and execution workflows to improve solution quality, reliability, and performance.
- Contribute to retrieval-augmented generation (RAG), knowledge grounding, search, vectorization, and information retrieval capabilities.
- Implement reliability, resiliency, and safety controls, including exception handling, monitoring, guardrails, validation logic, and escalation workflows.
- Develop automated testing, evaluation, and validation capabilities to ensure solution quality across releases, model updates, prompt changes, and workflow enhancements.
- Instrument solutions with telemetry, logging, and observability capabilities to support operational monitoring and troubleshooting.
- Participate in code reviews, contribute to engineering standards, and promote software engineering best practices across the organization.
- Create and maintain technical documentation, deployment procedures, operational runbooks, and support materials.
- Collaborate with product, architecture, platform, security, data, and quality engineering teams to deliver secure and scalable AI solutions.
- Contribute reusable components, reference implementations, and engineering patterns that improve platform adoption and team productivity.
Required QualificationsThe requirements listed below are representative of the knowledge, skill and/or ability required. Reasonable accommodations may be made to enable individuals with disabilities to perform the essential functions.
- Bachelor's degree in Computer Science, Software Engineering, a related field, or equivalent education, training, and work-related training.
- Minimum of 7 years of professional experience in software development.
- Deep knowledge of multiple programming languages, software architecture, and design principles.
- Deep understanding of software development lifecycle, testing, deployment, and security practices.
Preferred Qualifications- Strong expertise in Python and experience with modern software engineering practices and frameworks.
- Experience building AI-enabled applications using LLMs, agent frameworks, orchestration tools, retrieval systems, or related applied AI technologies.
- Experience integrating APIs, enterprise services, workflow platforms, and governed data sources into production solutions.
- Experience with software testing, code reviews, CI/CD pipelines, deployment automation, and operational support.
- Strong understanding of software architecture, application design patterns, and secure development practices.
- Demonstrated ability to independently execute well-scoped technical initiatives and deliver high-quality production outcomes.
- Strong written and verbal communication skills with the ability to work effectively in cross-functional delivery teams.
- Experience building agentic systems that incorporate tool calling, orchestration, retrieval, memory, and multi-step workflow execution.
- Experience with Microsoft Azure, Microsoft Copilot, Copilot Studio, Power Platform, or comparable enterprise AI ecosystems.
- Experience with RAG architectures, vector databases, enterprise search platforms, and knowledge-grounding solutions.
- Experience evaluating and improving AI system performance, accuracy, reliability, and business effectiveness.
- Experience working in highly regulated environments such as financial services, cybersecurity, healthcare, or other governance-driven industries.
- Experience contributing to engineering standards, conducting code reviews, and mentoring less experienced engineers.
- Experience supporting production AI systems through monitoring, telemetry analysis, incident response, and operational troubleshooting.
