Full Stack Engineer - Agentic Marketing Platform

Job Description

Insight Global is looking for a Full Stack Engineer to join the Marketing Technology Agentic Platform group with a large retail clients. In this role you will support building the next frontier of AI-native marketing infrastructure — intelligent, autonomous systems that power personalized marketing at Walmart scale (150M+ customers, 10,000+ stores, and the world's largest retailer). This group is not just building software; they are engineering a living network of AI agents that plan, create, optimize, and execute marketing campaigns across social channels, display, email, and beyond.

As a Full Stack Engineer on this team, you'll be at the epicenter of where Generative AI meets enterprise marketing. You'll design and build both the intelligent backend agents (Python, LLMs) and the sleek, real-time frontends (JavaScript/React) that orchestrate them. Your systems will connect to a federation of specialized agents via A2A (Agent-to-Agent) protocol and MCP (Model Context Protocol), forming an agentic mesh that can autonomously adapt campaigns, respond to market signals, and generate creative content — all at Walmart's global scale.

If you're excited about working at the cutting edge of Applied AI, love solving complex full-stack engineering problems, and want to see your work impact millions of customers and hundreds of billions in commerce — this is your team.

This role comes with an exceptional learning curve built into the job description. We invest in growing engineers who are curious and hungry to learn

Responsibilities:

• Deep, hands-on understanding of foundation models (GPT-4o, Claude 3.5, Gemini), model selection trade-offs, context windows, fine-tuning, and inference optimization
• Production-grade patterns for agentic systems — tool use, ReAct, chain-of-thought, self-correction, multi-agent coordination, and failure recovery
• End-to-end marketing intelligence: campaign lifecycle, audience segmentation, attribution, ROAS optimization, creative performance, and social channel mechanics
• Responsible AI practices at Walmart scale — brand safety, bias detection, privacy-preserving AI, and compliance guardrails in regulated marketing contexts
• Design, build, and operate LLM-powered marketing agents that autonomously plan and execute campaigns, generate ad copy, and optimize spend across social channels (Meta, TikTok, Pinterest, YouTube)
• Implement A2A (Agent-to-Agent) protocol integrations to compose multi-agent workflows — connecting specialized agents for audience targeting, creative generation, bid optimization, and analytics
• Build and extend MCP (Model Context Protocol) servers that expose marketing data, campaign APIs, and social channel connectors as context-aware tools consumable by LLM agents
• Architect agentic pipelines that chain reasoning, retrieval, tool use, and action — using frameworks like LangGraph, AutoGen, or custom orchestration layers
• Build React/Next.js frontends that give marketing teams real-time visibility into agent activity, campaign health, and AI-generated recommendations — with intuitive controls to guide, approve, or override agent decisions
• Develop Python FastAPI / Flask backends that serve as the orchestration layer between LLM agents, marketing APIs, and data pipelines
• Design and implement REST and streaming APIs that support real-time agent output (SSE / WebSockets) for live campaign dashboards Integrate with social channel APIs (Meta Graph API, TikTok Marketing API, Google Ads API) for programmatic campaign management

Skills and Requirements

• 6+ years of professional software engineering experience in production environments
• Strong JavaScript / TypeScript proficiency: React, Next.js, state management (React) async patterns, and browser performance optimization
• Strong Python proficiency: async Python (asyncio), REST API development (FastAPI / Flask), data processing, and scripting
• Hands-on experience working with Large Language Models (LLMs) — calling LLM APIs, designing prompt templates, and handling model outputs programmatically
• Practical understanding of LLM token concepts: context window limits, tokenization, prompt/completion token ratios, cost estimation, and strategies for fitting tasks within token budgets
• Experience building or consuming AI agent frameworks (e.g., LangChain, LangGraph, AutoGen, CrewAI, or custom orchestration)
• Solid foundation in REST API design, HTTP, and working with third-party APIs
• Proficiency with Git and collaborative engineering workflows (PRs, code review, CI/CD)
• Experience with cloud platforms (GCP, AWS, or Azure) — deploying services, working with managed databases, queues, and storage
• Familiarity with containerization (Docker, Kubernetes) and deploying services to cloud-native environments
• Understanding of prompt engineering principles: zero-shot, few-shot, chain-of-thought, structured output prompting.

We are a company committed to creating diverse and inclusive environments where people can bring their full, authentic selves to work every day. We are an equal employment opportunity/affirmative action employer that believes everyone matters. Qualified candidates will receive consideration for employment without regard to race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request to [email protected].