Agentic AI Engineer

Verizon•Irving, TX

23h•$101,000 - $194,000•Hybrid

About The Position

We are seeking an Agentic AI Engineer to architect and implement autonomous, multi-agent workflows that go beyond static text generation. You will be responsible for building reliable agentic systems that interface with enterprise databases, execute real-world APIs, manage long-term state, and operate safely within strict performance and governance guardrails.

Requirements

Bachelor's degree or four or more years of work experience.
Four or more years of relevant experience required, demonstrated through one or a combination of work and/or military experience, or specialized training.
Experience building Multi-Agent Systems with complex delegation models (human-in-the-loop escalation paths).
Hands-on experience developing enterprise-grade agentic workflows, multi-agent topologies, and task orchestration pipelines using platforms such as LangGraph, Google ADK / CES, Sierra, Decagon, or similar
Experience with Large Language Models (LLMs), prompt engineering, retrieval-augmented generation (RAG) architectures, and generative AI guardrails.

Nice To Haves

Bachelor's Degree in Computer Science, Computer Engineering, Artificial Intelligence, or a related technical field.
Experience in programming in modern languages (Python, Java, NodeJS) for building custom fulfillment webhooks, microservices, and backend APIs.
Experience implementing Vertex AI Search / Enterprise Search, grounding models, custom data store connectors, and tuning search relevance and rankings.
Experience integrating Google AI solutions with non-Google enterprise architectures via REST/SOAP APIs, pub/sub messaging, and webhook integrations.
Knowledge of contact center integrations (telephony adapters, CRM platforms like Salesforce/Genesys, and live agent hand-off protocols).

Responsibilities

Design stateful, multi-step agentic workflows using reasoning frameworks (e.g., ReAct, Plan-and-Solve, Reflection).
Build reliable execution layers connecting LLMs to external systems via REST APIs, database connectors, and protocol standards like Model Context Protocol (MCP).
Implement short-term and long-term memory architectures, state persistency, context window optimization, and hybrid RAG retrieval layers.
Establish offline test sets ("golden sets") and real-time observability pipelines (using LLM-as-a-judge, trace analysis, and latency/cost monitoring) to prevent hallucinations, infinite loops, and unwanted drift.
Containerize and deploy multi-agent microservices using scalable async patterns, distributed queues, and fallback mechanisms.