AI Systems Architect - LLM & Vector Infrastructure

Supabase (pgvector)RAG architecturesPrompt evaluation frameworksExperience designing scalable APIsWe are seeking a senior AI Systems Architect to design and implement AI-native application cores where Large Language Models (LLMs), vector databases, retrieval systems, and agent frameworks form the primary computational layer of our web and mobile applications.This role is responsible for architecting scalable AI pipelines, retrieval-augmented generation (RAG) systems, memory architectures, AI agents, and orchestration workflows integrated with our development stack (Web, Mobile, n8n automation, and AI services).The ideal candidate understands that AI is not a feature, it is the operating system of the product.Key ResponsibilitiesAI Core Architecture DesignDesign AI-first system architecture for web and mobile applicationsArchitect RAG pipelines using vector databasesDefine long-term memory, short-term memory, and contextual state systemsImplement multi-agent AI systemsDesign AI orchestration layersVector Database & Embedding SystemsPineconeWeaviateQdrantMilvusSupabase (pgvector)Optimize embedding strategiesImplement hybrid search (semantic + keyword)Design scalable indexing pipelinesLLM Integration & OptimizationOpenAI APIsAnthropicMeta (LLaMA)DeepSeekAlibaba (Qwen)Implement structured output pipelinesDesign evaluation and prompt testing frameworksOptimize cost-performance ratioAI Agent Systems & OrchestrationBuild autonomous AI agentsDesign tool-calling systemsIntegrate with:n8nLangGraph / LangChain style agent flowsImplement memory-aware agentsProduction AI EngineeringBuild monitoring systems for hallucination detectionDesign guardrails and validation layersImplement evaluation datasets and benchmarkingEnsure security of AI pipelinesBuild scalable infrastructure (Docker, Kubernetes, GPU optimization)RequirementsTechnical Expertise5+ years software engineering experience2+ years building production AI systemsDeep knowledge of:Vector embeddings & similarity searchRAG architecturesTokenization and context window optimizationFine-tuning & LoRA conceptsPrompt evaluation frameworksExperience with Python (mandatory)Experience with FastAPI / backend servicesExperience designing scalable APIsArchitecture ExperienceDesigning distributed systemsMicroservices & event-driven architectureExperience with PostgreSQL + pgvectorExperience deploying LLM systems in production#J-18808-Ljbffr