Summary: Seeking a solution-oriented AI Engineer to design and build production-grade multi-agent LLM systems, focusing on systems engineering and architecture. Highlights: 1. Design and build production-grade multi-agent LLM systems 2. Focus on systems engineering and architecture for reliable AI 3. Work independently with strong ownership and autonomy We are looking for a solution\-oriented **AI Engineer** who can design and build production\-grade multi\-agent LLM systems. The key expectation is not just writing code, but understanding the desired user outcome and engineering systems that reliably deliver it. This role is closer to systems engineering / architecture than classical ML. You will work independently, explore our APIs and product flows, and build agent\-based solutions that integrate deeply with the platform. **Context** ----------- * Product platform with multiple internal APIs * Agents interact with platform APIs and product workflows * High variability of use cases and flows * Relatively small data volumes per agent, but **high orchestration complexity** * Agents must operate autonomously with **tools, routing, memory and fallback strategies** * Backend stack mainly **Python**, frontend **TypeScript** **Role Responsibilities** ------------------------- * **Agent Architecture and System Design** * Design and implement multi\-agent systems, including orchestrator and worker agents * Define agent architecture, including routing, memory, tool usage, and fallback strategies * Translate product requirements into scalable and reliable agent workflows * Ensure systems are designed for robustness, maintainability, and extensibility * **Agent Infrastructure and Development** * Build core infrastructure for agent execution, including tool calling and state management * Develop and maintain multimodal pipelines (text and image generation) * Integrate and abstract multiple model providers (e.g., OpenAI, Anthropic, self\-hosted models) * Implement custom tools and services to extend agent capabilities * **Platform Integration** * Integrate agents with internal platform APIs and product workflows * Analyze API specifications and existing codebases (Python backend and TypeScript frontend) * Build adapters and integration layers where necessary * Ensure reliable interaction between agents and platform systems * **Reliability, Testing, and Evaluation** * Implement testing strategies for agent behavior and system reliability * Build evaluation pipelines to measure LLM and agent performance * Debug complex agent workflows and improve system stability * Contribute to observability, logging, and monitoring of AI systems * **Cross\-functional Collaboration** * Work closely with Product and Engineering teams to define use cases and system behavior * Provide input on AI architecture and system design decisions * Contribute to best practices for building production\-grade AI systems **Required Qualifications** --------------------------- * Strong Python backend development experience, including async programming and APIs * Commercial experience building multi\-agent LLM systems (required) * Experience with agent frameworks such as LangChain, LangGraph, AutoGen, CrewAI, LlamaIndex, or similar * Experience designing agent orchestration, tool usage, routing, and memory systems * Experience building multimodal pipelines * Experience integrating multiple model providers (e.g., OpenAI, Anthropic, self\-hosted models) * Experience working with vector databases (e.g., Qdrant, Pinecone, Weaviate) * Experience with Redis or similar systems for caching and state management * Strong understanding of production\-grade development practices, including testing and debugging * Ability to design systems that prioritize reliability over experimentation **Nice to have** ---------------- * ML background or practical ML knowledge * Experience designing **AI product architectures** * Experience building **agent evaluation / benchmarking frameworks** * Experience working with **large API ecosystems** * Experience with AI observability tools **Working Style** ----------------- * Strong **ownership and autonomy** * Ability to work from **problem architecture implementation** * Comfortable exploring unfamiliar codebases, APIs and product logic * Focus on **engineering reliable AI systems**, not just experimenting with models ***Aghanim helps game developers achieve financial and creative independence by providing the solutions they need to launch, run, and grow their businesses.***