Agentic AI Architect

Role: AI Architect – Agentic Workflows & Customer Journey
Location: Denver, CO Preferred, Open for Stamford , CT & Charlotte NC
Duration: 12 Months
Video Interview

Role Overview:

Customer is seeking an AI Architect to lead the technical design, orchestration, and implementation of our next-generation Agentic AI ecosystem.
Reporting into the Customer Journey AI team, you will design the blueprints that allow autonomous, goal-oriented AI agents to execute complex, end-to-end workflows across all customer touchpoints—including digital portals, the Spectrum TV App, conversational IVR, messaging, and retail/field operations.
 You will build the framework that transitions our customer experience from static chatbots to proactive, autonomous agents capable of real-time reasoning, tool use, and safe backend integration.
To implement Agentic AI workflows across all customer journeys, an AI Architect would need to bridge the gap between cutting-edge LLM orchestration and massive legacy telecom architectures (like BSS/OSS, CRM, and billing systems).
Unlike a traditional data science role, this architect focuses on multi-agent systems, real-time tool use, and safety guardrails to ensure autonomous agents can safely resolve customer issues (like billing disputes or network troubleshooting) without human intervention.
 Core Responsibilities Agentic Framework Architecture: Design and implement a scalable, highly available architecture for multi-agent systems, utilizing state-of-the-art frameworks (e.g., LangGraph, AutoGen, CrewAI, or proprietary orchestration layers) to handle complex customer intents.

 Context & State Management: Architect robust, low-latency state-management systems that allow AI agents to maintain context across multi-session, multi-channel customer journeys (e.g., transferring a digital chat context seamlessly to a live call center agent).
API & Tool Integration (Function Calling): Design safe, secure, and standardized interfaces enabling LLM agents to accurately call tools, query databases, and execute actions within Charter’s legacy BSS/OSS, billing platforms (e.g., CSG/Amdocs), and network telemetry systems.
Guardrails & Deterministic Safety: Build and maintain deterministic validation layers, evaluation pipelines, and guardrail frameworks (e.g., NeMo Guardrails, Llama Guard) to ensure agent behavior complies with strict telecom compliance, privacy laws, and brand guidelines.
RAG & Memory Architecture: Optimize Retrieval-Augmented Generation (RAG) pipelines and vector database infrastructure to give agents instantaneous access to thousands of internal knowledge bases, equipment manuals, and structured account schemas.
Cross-Functional Technical Leadership: Collaborate closely with Software Development, Data Engineering, DevOps, and Product teams to transition legacy customer touchpoints into AI-native interfaces.
Required Qualifications & Technical Skills Experience:
10+ years in enterprise software architecture, with at least 3+ years specifically dedicated to production-grade AI/ML systems and LLM orchestration.
Agentic Orchestration: Proven track record of deploying systems utilizing multi-agent collaboration, autonomous reasoning (ReAct patterns), and complex function calling.
AI Stack: Advanced proficiency with Python, vector databases (e.g., Pinecone, Milvus, pgvector), and LLM frameworks.
Experience with open-source and commercial models (OpenAI, Anthropic, Llama, Mistral).
Data & Cloud Architecture: Deep experience with AWS or Google Cloud AI infrastructure, streaming data pipelines (Kafka, Flink), and caching strategies (Redis) for low-latency inference.
Integration Expertise: Familiarity with integrating AI layers on top of high-transaction enterprise architectures, REST/GraphQL APIs, and microservices.

 Preferred Qualifications

Telecom Domain Knowledge: Prior experience working with telecommunications customer data models, billing systems (Amdocs, CSG), or network operations.
Advanced Evaluation Frameworks: Experience setting up automated evaluation rigs (e.g., Ragas, TruLens) to continuously score agent accuracy, hallucination rates, and task completion metrics in production.