AI Agent Engineer

LaunchPad Lab•Chicago, IL

5h•$125,000 - $175,000•Remote

About The Position

LaunchPad Lab is a Chicago-based software development consultancy with 14+ years of building custom platforms for organizations that need more than off-the-shelf solutions. We have gone all-in on AI. Our AI practice helps mid-market and enterprise clients design, build, and deploy AI agents that transform how their businesses operate. We are hiring an AI Agent Engineer to be the technical engine behind this work. This is a hands-on, high-autonomy role: you will design, build, and deploy AI agent systems for clients, drive internal agent-powered automation for LaunchPad Lab itself, and help define what great AI agent development looks like across the consultancy. Your time will be split roughly 50/50 between client-facing agent development and internal AI initiatives. You will report to the CTO. We’re looking for an agent builder who can sit with a client, identify where autonomous workflows create real leverage, design the agent system, and ship it.

Requirements

2+ years of professional software engineering experience with strong fundamentals.
2+ years of hands-on experience building AI agent systems, including autonomous or semi-autonomous agents deployed in production environments.
Deep working knowledge of agent orchestration frameworks (LangChain, LangGraph, CrewAI, LlamaIndex, Claude Managed Agents, or equivalent). You should have opinions about their tradeoffs.
Experience with agent design patterns including prompt engineering, RAG architectures, tool/function calling, agent memory management, and evaluation frameworks.
Experience with MCP (Model Context Protocol), A2A (Agent-to-Agent Protocol), or other emerging agent interoperability standards.
Demonstrated ability to lead client-facing technical conversations, translate business problems into technical solutions, and present to senior stakeholders.

Nice To Haves

Consulting or agency experience delivering technical projects for external clients.
Familiarity with infrastructure for AI workloads: vector databases (Pinecone, Weaviate, pgvector), cloud platforms (AWS, Azure, or GCP), and observability tools (LangSmith, PostHog, or OpenTelemetry).
MLOps experience: comfortable with LLM monitoring, agent observability, eval design, and guardrail implementation to keep agent systems reliable and safe in production.
Experience building internal tools or automations that improved operational efficiency.
Hands-on experience with workflow automation and AI agent platforms such as Workato, Cassidy AI, n8n, Claude, or Claude Managed Agents.

Responsibilities

Design and build production AI agent systems for clients across industries, from scoping through deployment and iteration.
Lead technical discovery workshops to identify high-value automation opportunities in client workflows.
Select and integrate the right agent frameworks, platforms, and models for each engagement (LangChain, LangGraph, CrewAI, Claude Managed Agents, custom orchestration, and others as the landscape evolves).
Design human-in-the-loop workflows, approval gates, and escalation paths so agent systems operate safely in client environments, especially in regulated or risk-sensitive industries
Translate complex AI capabilities into clear, actionable recommendations for non-technical stakeholders.
Collaborate with LaunchPad Lab’s engineering and design teams to deliver end-to-end solutions.
Own LaunchPad Lab’s internal agent automation roadmap. Identify processes ripe for agent-driven improvement and build the solutions.
Evaluate new agent frameworks, platforms, and tooling.
Develop reusable agent architectures, prompt libraries, and patterns that accelerate delivery across the consultancy.
Contribute to the AI practice’s positioning, thought leadership, and go-to-market efforts with technical credibility.
Mentor other engineers on AI patterns, tools, and best practices as the practice grows.