Principal AI Agent Engineer – Agentic AI & LLM Applications

AT&T•Atlanta, GA
•$155,400 - $261,100•Onsite

About The Position

The Business Agent Foundry is seeking a Principal AI Agent Engineer to design, build, and scale production-grade AI agents and LLM-powered applications that address high-value business problems. This role works directly with business partners to translate complex or ambiguous needs into AI-enabled solutions, moving from problem definition and prototyping to production while maintaining standards for security, reliability, observability, Responsible AI, and maintainability. The engineer will build and deploy conversational, workflow, and task-oriented agents that can use tools, APIs, enterprise data, retrieval, structured reasoning, and human-in-the-loop approvals. The role includes developing agent orchestration, integrating enterprise systems and data, implementing retrieval and evaluation strategies, and establishing monitoring, guardrails, and reusable engineering patterns. The position requires demonstrated experience shipping AI agents, LLM applications, or GenAI workflow automation into production and explaining their adoption and measurable business impact. This is a full-time, onsite role performed at a designated work location five days per week. No relocation is offered. Locations listed include Alpharetta, Georgia; Dallas and Plano, Texas; and Atlanta, Georgia.

Requirements

  • Demonstrated experience building and shipping AI agents, LLM-powered applications, or GenAI workflow automation into production for real users or business teams.
  • Ability to explain the scope and impact of previously deployed AI systems, including architecture, users, workflows, data sources, integrations, adoption, operating model, and measurable business outcomes.
  • Deep hands-on experience with Python and backend or full-stack development using technologies such as FastAPI, Flask, or Django.
  • Strong understanding of LLM application architecture, including prompt engineering, context engineering, RAG, tool or function calling, session state, structured outputs, and response validation.
  • Hands-on experience with agent orchestration frameworks such as LangGraph, Semantic Kernel, AutoGen, CrewAI, or comparable platforms.
  • Experience designing APIs, service integrations, authentication, database interactions, and deployment-ready application components.
  • Experience connecting AI applications to enterprise data, APIs, knowledge repositories, vector databases, or systems of record.
  • Strong software engineering discipline across automated testing, code review, CI/CD, logging, monitoring, observability, and production support.
  • Ability to evaluate tradeoffs among AI models based on accuracy, latency, cost, reliability, risk, and business requirements.
  • Strong communication skills and ability to explain complex AI and engineering decisions to technical and non-technical stakeholders.
  • Typically 8+ years of software engineering experience, including experience designing and operating complex production systems.
  • Significant hands-on experience developing and deploying LLM, GenAI, or agentic AI applications.
  • Strong proficiency in Python, APIs, distributed application architecture, and enterprise integration.
  • Experience with at least one production-capable agent or AI orchestration framework.
  • Experience implementing evaluation, monitoring, observability, and reliability controls for AI-enabled applications.
  • Understanding of Responsible AI, data privacy, security, access control, auditability, and AI guardrails.
  • Ability to work in an onsite, highly collaborative environment with business and technology partners.

Nice To Haves

  • Technical leadership experience establishing architecture, engineering standards, or reusable patterns across multiple teams.
  • Experience applying AI within enterprise functions such as customer care, operations, network, sales, finance, service delivery, or employee productivity.
  • Experience with advanced RAG, knowledge graphs, enterprise search, ontology-driven retrieval, or semantic data modeling.
  • Experience evaluating or serving LLMs at scale, including quality, latency, token or cost, and reliability optimization.
  • Front-end development, data visualization, or rapid product prototyping experience.
  • Open-source contributions or reusable frameworks related to AI agents, LLM applications, AI evaluation, or GenAI engineering.

Responsibilities

  • Design, build, and deploy production-grade AI agents and agentic workflows to improve customer experience, employee productivity, operational efficiency, quality, or cost.
  • Partner with business leaders, product teams, and process owners to identify high-value AI opportunities and translate ambiguous requirements into scalable solutions.
  • Build conversational, workflow, and task-oriented agents that use tools, APIs, enterprise data, retrieval, structured reasoning, and human-in-the-loop approvals.
  • Develop agent orchestration using LangGraph, Semantic Kernel, AutoGen, CrewAI, Bedrock Agents, or similar production-capable frameworks.
  • Engineer prompts, system instructions, context-management strategies, state, memory, and retrieval flows to improve accuracy and reliability.
  • Integrate AI solutions with enterprise APIs, databases, knowledge repositories, systems of record, vector stores, and other data sources.
  • Implement RAG and advanced retrieval patterns, including enterprise search, semantic retrieval, and context engineering.
  • Establish evaluation frameworks using golden datasets, scenario testing, regression testing, human review, and production feedback loops.
  • Build observability across prompts, model calls, retrieval, tool execution, latency, errors, and user interactions.
  • Design guardrails, escalation paths, human oversight, and secure access patterns for sensitive or higher-risk workflows.
  • Apply Responsible AI, privacy, security, and governance principles throughout solution design and deployment.
  • Establish reusable engineering patterns, templates, and components for other teams to use across the AI platform.

Benefits

  • Medical, dental, and vision coverage
  • 401(k) plan
  • Tuition reimbursement program
  • Paid Time Off and holidays, including at least 23 vacation days each year and 9 company-designated holidays, based on date of hire
  • Paid parental leave
  • Paid caregiver leave
  • Additional sick leave beyond what state and local law require may be available but is unprotected
  • Adoption reimbursement
  • Short-term and long-term disability benefits
  • Life and accidental death insurance
  • Supplemental benefit programs, including critical illness, accident hospital indemnity, and group legal
  • Employee Assistance Programs (EAP)
  • Employee wellness programs
  • Employee discounts up to 50% off eligible AT&T mobility plans and accessories, AT&T internet (and fiber where available), and AT&T phone
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service