AI Platform Engineer

Introduction

At Ironbelly, we are fundamentally changing how video games are made. Our AI team, led by industry luminaries and veterans, is building GameFrame AI —a platform that allows developers to create complex, professional games using natural language. We are the creators of a battle-tested gameplay framework that has been used to build and launch AAA games, and we're leveraging that expertise to architect the future of creative software.

This isn't just another AI wrapper. You'll be engineering a production-scale AI orchestration system that coordinates specialized agents to manipulate Unreal Engine in real-time, building technology that has never existed before.

A Note on the Role: This is an Applied AI Engineering Position

To ensure we're connecting with the right candidates, let's be clear about the focus of this role:

• ✅ We ARE looking for: A seasoned backend/platform engineer with production experience building complex systems that use AI models and frameworks (like LangChain, LLM APIs, LLM workflows).

• ❌ This is NOT: A Machine Learning research or AI model-building role. We are not developing novel neural network architectures or training models from scratch.

What You'll Build ️

As a Senior Software Engineer on our AI Platform, you will architect the intelligent backend that enables conversational game development.

• Advanced Multi-Agent Orchestration: Design and build the core of GameFrame AI, implementing sophisticated multi-agent (LangGraph Swarm) and single-agent (ReAct) systems that translate user requests into concrete game development actions.

• Gameplay Framework Integration: Engineer the crucial link between our AI systems and Unreal Engine, developing a robust translation layer that allows AI agents to programmatically configure our proprietary, component-based gameplay framework.

• Production AI Infrastructure: Architect and scale a distributed, multi-user backend on cloud infrastructure (AWS/GCP, Kubernetes). You'll build everything from multi-provider LLM orchestration and hybrid memory systems to real-time streaming responses over WebSockets.

• System Reliability & Observability: Implement enterprise-grade observability, monitoring, and robust failover systems required to support thousands of concurrent users with sub-second response times.

Who We're Looking For

We are seeking a strong software engineer who is passionate about building at the intersection of AI and game development.

Must-Have Experience:

• Expert-Level Backend Engineering: Deep, production-level experience in Python (3.11+), building microservices with frameworks like FastAPI, and designing with async/await patterns.

• Production Systems: Proven experience with PostgreSQL, Redis, real-time WebSocket systems, and container orchestration using Docker and Kubernetes in a cloud environment (AWS/GCP).

• Applied AI Systems: 1+ years of hands-on experience building applications that leverage AI systems. You have practical, high-level experience with frameworks like LangChain/LangGraph and tooling like Claude Code.

• Game Development Context: A strong understanding of Unreal Engine concepts (Actors, Components, Blueprints) and workflows, gained through at least 2 years of professional or significant personal project experience.

Nice-to-Have Experience:

• Experience building production React applications with TypeScript and Next.js.

• Advanced prompt engineering techniques (e.g., Chain-of-Thought).

• Experience designing and implementing evaluation frameworks for AI agent performance.

Your Impact & Growth

• First 90 Days: Architect and deploy the core agent systems for game creation, implementing multi-provider LLM orchestration and production-grade memory systems.

• 6-12 Months: Scale the platform to support 500+ concurrent users, launch advanced agent capabilities, and build out continuous learning systems for our AI.

• 12+ Months: Lead technical strategy as we scale to thousands of users, contribute to new industry patterns for AI-driven creative software, and help establish our position as thought leaders in the space.

Our Culture & Benefits

We are a passionate team based in

Montreal with a hybrid model that gets us collaborating in the office 1-2 days a week. We offer a competitive salary and a significant equity package with high growth potential.

Comprehensive Benefits: Health, dental, and vision package , plus flexible PTO.

• Growth & Learning: A professional development budget for conferences, a hardware stipend, and dedicated research time to stay at the cutting edge.

• Unique Perks: Opportunities for conference speaking, dedicated time for open-source contributions, and direct access to cutting-edge AI research partnerships.