Princ Engr-ntwk Engring

Verizon Verizon · Telecom · Basking Ridge, NJ +2

This Principal Engineer role focuses on developing and deploying AI-powered bots and automated agents to streamline network capacity planning workflows. The role involves designing, building, and fine-tuning LLM integrations, developing agentic AI workflows for multi-step task orchestration, and engineering RPA solutions. It also includes data engineering tasks for creating unified analytical models and maintaining vector databases, as well as developing machine learning forecasting models and MLOps practices.

What you'd actually do

  1. Design, develop, and deploy AI-powered bots and automated agents that streamline PSC capacity workflows, data ingestion pipelines, and reporting cycles across UNIX-based environments.
  2. Build and fine-tune large language model (LLM) integrations (e.g., Claude, GPT-4, Gemini) using prompt engineering, Retrieval-Augmented Generation (RAG), and function/tool-calling frameworks to automate analysis and generate leadership-ready readouts.
  3. Develop agentic AI workflows using frameworks to orchestrate multi-step capacity planning tasks end-to-end with minimal human intervention.
  4. Create Python-based automation scripts, ETL pipelines, and REST/GraphQL API integrations to pull data from COEP, 1ERP/NSAP/vSAP, dcTrack, Canvas, Clarity, and other network management systems into unified analytical models, leveraging SQL, PostgreSQL, Oracle, SQL Server, and Hadoop DFS for data storage and processing.
  5. Engineer Robotic Process Automation (RPA) solutions to replace high-volume, repetitive manual tasks across PSC planning workflows.

Skills

Required

  • Python
  • LLM integration
  • Prompt Engineering
  • RAG
  • Tool/Function Calling
  • Agentic Workflows
  • ETL
  • API Integration
  • SQL
  • RPA
  • Vector Databases
  • MLOps
  • Machine Learning Forecasting
  • AWS/Azure/Kubernetes
  • Git/SVN

Nice to have

  • Claude
  • GPT-4
  • Gemini
  • UNIX
  • COEP
  • 1ERP/NSAP/vSAP
  • dcTrack
  • Canvas
  • Clarity
  • PostgreSQL
  • Oracle
  • SQL Server
  • Hadoop DFS
  • Looker
  • Tableau
  • OpenRAN
  • vRAN
  • edge compute

What the JD emphasized

  • AI-powered bots and automated agents
  • agentic AI workflows
  • large language model (LLM) integrations
  • prompt engineering
  • Retrieval-Augmented Generation (RAG)
  • function/tool-calling frameworks
  • orchestrate multi-step capacity planning tasks
  • Python-based automation scripts
  • ETL pipelines
  • REST/GraphQL API integrations
  • SQL
  • PostgreSQL
  • Oracle
  • SQL Server
  • Hadoop DFS
  • Robotic Process Automation (RPA)
  • vector databases
  • semantic search capabilities
  • chatbot interfaces
  • MLOps practices
  • model versioning
  • automated retraining pipelines
  • performance monitoring
  • drift detection
  • predictive capacity models
  • AWS
  • Azure
  • Kubernetes
  • Git/SVN
  • machine learning forecasting models
  • regression
  • time-series
  • ensemble methods
  • quantified confidence intervals
  • AI/automation roadmaps
  • technical user stories
  • Agile/Scrum ceremonies

Other signals

  • AI-powered bots and automated agents that streamline PSC capacity workflows
  • Build and fine-tune large language model (LLM) integrations
  • Develop agentic AI workflows using frameworks to orchestrate multi-step capacity planning tasks end-to-end