Quantum World Technologies logo

Senior / Lead Software Engineer – AI Agents (GCP)

Quantum World Technologies

HybridAtlanta, GAleadPosted 2h ago

Job description

Senior / Lead Software Engineer – AI Agents (GCP)

Location: Atlanta, GA – 3 Days Onsite

Duration: Long Term Contract

Position Overview

We are seeking a highly skilled

Senior / Lead Software Engineer – AI Agents

to design, build, and deploy production-grade

AI agents and chatbots on Google Cloud Platform (GCP)

.

The ideal candidate will have strong software engineering experience combined with hands-on expertise in

AI/LLM applications, Python, Google Cloud, Vertex AI, Agent Development Kit (ADK), APIs, distributed systems, and SQL/BigQuery

.

This role will own the complete AI agent delivery lifecycle, from

rapid Proof of Concept (POC) through production deployment

, while ensuring solutions are secure, scalable, reliable, observable, and cost-effective.

Key Responsibilities

AI Agent & Chatbot Development

  • Design and develop

    AI agents and enterprise chatbots

    using modern agent frameworks.

  • Build agents capable of interacting with:

  • APIs

  • Databases

  • Enterprise applications

  • Cloud services

  • External tools

  • Develop tool-calling and service-integration capabilities for AI agents.

  • Implement multi-step agent workflows involving

    reasoning, orchestration, context management, and tool execution

    .

Google Cloud & ADK

  • Develop AI agents using

    Google Agent Development Kit (ADK)

    .

  • Build primarily with

    Python

    , with Java or another backend language as applicable.

  • Leverage

    Google Cloud Platform

    services to build scalable AI solutions.

  • Work extensively with

    Vertex AI

    and other GCP services.

  • Deploy production services using

    Cloud Run and/or GKE

    .

  • Integrate AI agents with

    BigQuery and enterprise systems

    .

POC to Production

  • Rapidly prototype AI agent solutions using

    Agent Studio, AI Studio, or equivalent tools

    .

  • Quickly evaluate concepts and demonstrate working AI solutions.

  • Convert successful POCs into

    production-ready services

    .

  • Establish reusable patterns and frameworks for moving AI solutions from experimentation to enterprise production.

  • Identify and resolve technical challenges during productionization.