Senior AI Engineer (Agentic Systems)

About Us
We are an established and successful entrepreneurial team now launching our next major venture: a cutting-edge autonomous agency powered by a team of collaborative AI agents. We are moving beyond simple chatbots to build a true digital workforce. You will be joining a well-resourced project backed by seasoned founders, offering the excitement of a ground-floor opportunity combined with the stability and experience of a proven team.
This is a chance to get in on Day 1 and become the foundational engineer of a system designed to be at the forefront of the agentic AI revolution.
The Role: Senior AI Engineer
We are looking for a highly skilled and motivated Senior AI Engineer to be our first dedicated technical hire. You will be the "Doer" who works alongside our strategic "Thinker" agents to build, deploy, and manage our entire AI ecosystem. You will be responsible for turning architectural designs into robust, production-ready code and infrastructure.


This is a full-time, remote position. We require significant overlapping hours with the US Central Time (CST) morning for daily collaboration.


Key Responsibilities:
Take the lead on building and deploying our core AI agents using Python, LangChain, and various LLM APIs.
Design, build, and maintain the API infrastructure (using FastAPI) that allows our agents to communicate with the world.
Set up and manage the cloud infrastructure, databases (SQL and Vector), and automation platforms (n8n) that our agents rely on.
Implement and manage a secure system for API keys and credentials.
Work with our CSO (Chief Strategy Officer) agent to design and implement new workflows and capabilities, including a "self-updating" mechanism for the agents themselves.
Ensure all systems are properly logged, monitored, and optimized for cost and performance.
The Mission: Build the Foundational AI Operating System
Your primary mission is to be the architect and builder of our company's new AI Operating System. This is not a one-off project; you are creating the core engine that will power a new generation of autonomous business units. Your initial sprint will be to bring the Minimum Viable Product (MVP) to life, proving the system's core capabilities.
Your First Sprint: The "Think & Do" Loop MVP
We have a clear, aggressive plan to get our foundational AI team operational within the first 5-6 weeks. Your mission will be to:
Week 1: Foundation: Rapidly deploy the core infrastructure: secure cloud hosting, interconnected databases (SQL & Vector), secrets management, and the n8n automation hub. This is the ground on which everything else is built.
Following Weeks: The Build: Construct and deploy our first two agents—the CSO ("The Thinker") and the AI Engineer ("The Doer"). This involves deep integration with LLM APIs, our memory systems, and the Slack workspace.
The MVP Goal: Implement the critical "self-updating" workflow. This will enable an agent's core programming to be modified via a simple Slack message, with final human approval, proving the system can improve itself.
The Long-Term Vision: A Repeatable, Scalable Platform
Success in this first sprint is just the beginning. The architecture you build will serve as the master blueprint. The ultimate goal is to create a robust and repeatable system that can be cloned and adapted to launch new, specialized AI teams for additional business units. The work you do in these first months will directly enable our ability to scale from one AI team to many, making you a pivotal figure in the company's future.
Qualifications (Must-Haves):
Proven professional experience in Python development.
Strong experience building and deploying REST APIs (FastAPI, Flask, or similar).
Hands-on experience deploying applications to a cloud platform (e.g., Render, AWS, GCP, DigitalOcean).
Demonstrable experience integrating with at least one major LLM API (e.g., OpenAI, Anthropic, Google Gemini).
A strong understanding of security best practices, especially regarding API key and secret management.
Qualifications (Nice-to-Haves - A Big Plus!):
Direct experience with AI agent frameworks like LangChain, LlamaIndex, etc.
Familiarity with multi-agent systems (Autogen, CrewAI).
Knowledge of different database technologies (e.g., PostgreSQL, and Vector Databases like Pinecone or Weaviate).
Experience with workflow automation tools like n8n or Zapier.
Experience setting up CI/CD pipelines and monitoring tools.
Compensation:
This is a full-time role.
The hourly rate is competitive and will be determined based on your experience and performance in our technical challenge.
How to Apply:
To begin the process, you will be invited to complete a short, practical technical challenge that allows you to showcase your skills in a real-world scenario. We look forward to seeing what you can build.