Role Overview We’re looking for a hands-on and visionary Founding Engineer to lead the design and implementation of cutting-edge LLM and Voice System architectures. This is a full-time, remote role (preferably based in LatAm or the US) focused on building scalable AI infrastructure from the ground up. What You’ll Lead & Build: Full-stack LLM infrastructure, including prompts, embeddings, and vector databases (e.g., Pinecone, Weaviate) Scalable, multilingual RAG systems trained on real-world case data Voice-to-intent pipelines using Whisper or more advanced tools Intelligent, tool-using agents for diagnostics, repair, and procurement tasks GEO (Generative Engineering & Operations) systems — including agent orchestration, contextual memory, and feedback loops Real-time performance optimization across voice, text, and structured data Full lifecycle ownership — from prototypes to market-ready production systems You’re a Great Fit If You: Bring 7+ years of experience in ML/NLP, with 2+ years in generative AI Have led architecture and scaling of agentic or multimodal AI systems Have successfully launched LLM-powered products to production Know tools like LangChain, LlamaIndex, and vector databases deeply Have real-world experience deploying effective RAG pipelines Prioritize latency, user experience, and cost-efficiency Are fluent in English (Spanish/Portuguese is a plus) Thrive in fast-paced environments and want to shape a global product at scale