🎮 AI Platform Engineer – Gameframe 🚀
If you're excited about architecting novel AI systems, solving production engineering challenges at scale, and enabling human creativity through technology, we want to talk to you.
We usually respond within a week
🤖 Transforming Game Development Through AI 🎮
GameFrame AI is revolutionizing how games are created. We're not just another AI wrapper; we're architecting the future of creative development
The Challenge: Design and build sophisticated real-time interfaces that seamlessly blend conversational AI with game development workflows, supporting multi-agent coordination, real-time streaming responses, and complex game engine integrations - all while scaling to 1000's of concurrent users
The Role: AI Systems Architect 🚀
As our AI Platform Engineer, you will collaborate with our CTO to architect and build the core AI orchestration layer that powers our revolutionary platform. You'll be designing novel multi-agent systems that understand game development at a semantic level and coordinate complex workflows across distributed VM infrastructure.
You'll work at the intersection of cutting-edge AI research and production-scale systems engineering, building technology that has never existed before: real-time, multi-user AI orchestration for game development.
What You'll Build 🔧
Advanced Multi-Agent Orchestration
- Design and implement LangGraph Swarm architectures with 7+ specialized agents working in concert
- Build custom ReAct agents with sophisticated tool-calling capabilities and error recovery
- Implement constitutional AI layers for safety, consistency, and domain-specific constraints
- Create agent communication protocols for coordinating complex, multi-step game development tasks
- Implement intelligent context management for game development workflows
- Create continuous learning systems that improve agent performance through user interactions
Production AI Infrastructure
- Architect multi-provider LLM orchestration (OpenAI, Anthropic, Google) with intelligent fallback and cost optimization
- Build hybrid memory systems combining conversation, entity, and semantic memory with Pinecone vector search
- Implement real-time streaming AI responses integrated with WebSocket infrastructure
- Design distributed agent systems that scale across multiple VM instances and user sessions
Production-Scale Architecture
- Design session routing and VM orchestration for isolating user AI contexts
- Build auto-scaling AI infrastructure that handles traffic spikes while optimizing costs
- Implement comprehensive observability for AI systems with distributed tracing and performance monitoring
- Create robust error handling and failover systems for production reliability
Technical Environment 🛠️
AI/ML Stack
- Core: LangChain, LangGraph, Langsmith, Langfuse
- APIs: LiteLLM, OpenAI/Anthropic/Google
- Memory: Neo4j, Graphiti, Pinecone, Weaviate, Redis, custom embedding systems.
- Frameworks: Custom agent orchestration, constitutional AI layers
- Evaluation: Custom testing frameworks, performance monitoring
Backend Infrastructure
- API: FastAPI, Python 3.11+, async/await patterns
- Database: PostgreSQL 15, TimescaleDB, Redis caching
- Real-time: WebSocket, streaming protocols, pub/sub systems
- Infrastructure: Docker, Kubernetes, AWS/GCP, auto-scaling, tailscale, Portainer,
Integration Layer
- Game Engines: Unreal Engine, Unity
- VM Orchestration: Custom session routing, multi-user isolation
- Monitoring: Prometheus, Grafana, distributed tracing
Your Technical Expertise 💻
Required: AI/ML Systems Mastery
- 2+ years building production AI systems
- High-level LangChain/LangGraph experience including custom agents, state machines, memory systems, and chain optimization
- Deep neural network understanding including transformer architectures, attention mechanisms, embedding spaces, and model limitations
- Production RAG systems with advanced chunking strategies, reranking, hybrid search, and context optimization
- Multi-provider LLM integration with experience across OpenAI, Anthropic, Google, and local model orchestration
Required: Backend Systems Engineering
- Expert Python 3.11+ with FastAPI, async/await patterns, and microservices architecture
- Production database systems including PostgreSQL optimization, TimescaleDB, and Redis caching strategies
- Real-time systems with WebSocket management, streaming protocols, and low-latency processing
- Container orchestration with Docker, Kubernetes, and cloud infrastructure (AWS/GCP)
- Distributed systems design patterns, fault tolerance, and observability
Preferred: AI Research & Innovation
- Open-source contributions in AI/ML
- Advanced prompt engineering including few-shot, chain-of-thought, and tree-of-thought techniques
- Evaluation frameworks for automated testing of AI agent performance and prompt regression testing
- Mixture of Experts patterns and agent specialization architectures
Your Impact & Growth 📈
Immediate Impact (First 90 Days)
- Architect core agent systems for Movement and Combat specialists
- Implement multi-provider LLM orchestration with cost optimization
- Build production memory systems with Pinecone integration
- Design evaluation frameworks for agent performance monitoring
Platform Impact (6-12 Months)
- Scale to 500+ concurrent users with auto-scaling infrastructure
- Launch advanced agent capabilities including code generation and semantic understanding
- Implement continuous learning systems that improve through user interactions
- Build enterprise-grade observability and performance optimization
Industry Impact (12+ Months)
- Establish new patterns for AI-driven creative software architecture
- Contribute to open source and research in multi-agent systems
- Scale platform to support thousands of developers creating games
- Lead technical strategy as the platform evolves toward enterprise studios
Benefits 💰
Base Salary commensurate with experience
Equity: Significant equity package with high growth potential
Benefits Package:
- Health, dental, vision with company contribution
- Flexible PTO and remote/hybrid work arrangements
- Professional development budget for AI/ML conferences and research
- Hardware stipend for development equipment and cloud resources
- Research time allocated for staying current with AI developments
Unique Perks:
- Conference speaking opportunities as we establish thought leadership
- Open source contribution time for projects aligned with platform goals
- Direct access to cutting-edge AI models and research partnerships
- Creative project support for personal game development experiments
- Department
- AI
- Locations
- Eastern Europe, Western Europe, Canada , Québec, Canada, USA, Canada, Montreal, South America
- Remote status
- Hybrid
About Ironbelly Studios
Ironbelly Studios is comprised of a talented, passionate and dedicated number of game developers from all corners of the globe. Our focus is on creating high quality entertainment experiences as well as providing outsourcing services at a fraction of the cost seen elsewhere.
From humble beginnings Ironbelly has grown to be one of the most trusted names in the indie development space, working on over 300 projects in our 15 years of service, ranging from AAA titles such as Gotham Knights down to small mobile titles. We bring passion and experience together and look for people who put games and their creation in the center of their world.