AI ENGINEER - Role OverviewWe are looking for a hands-on AI/ML Engineer to implement production-grade, multi-agent systems. You will translate high-level architectural designs into robust Python code, focusing on reliability, latency, and the deterministic execution of agentic workflows.This role can be remote in Greece or Poland, or hybrid in our Dublin office.Key ResponsibilitiesDevelop Multi-Agent Workflows: Create agentic systems using frameworks like LangGraph and LangChain, implementing tool-calling, planning, and self-correction capabilitiesBuild Production RAG Systems: Design and implement sophisticated retrieval-augmented generation pipelines with multi-modal capabilities, handling text, tables, and complex document structures. Integration of Graph Databases with LLM systems for entity extraction, relationship mapping, and structured retrieval.Production Deployment: Deploy and monitor AI systems using Docker, Kubernetes, and CI/CD pipelines, ensuring reliability, scalability, and cost-effectivenessTechnical QualificationsCore Tech StackLanguages: Strong Python proficiency (asyncio, type hinting, Pydantic).AI Frameworks: Deep practical experience with LangChain, LangGraph, or LlamaIndex.Data Engineering: Experience with SQL and Vector Databases (Cosmos DB, Milvus, Chroma, or Pinecone, etc).API Development: Experience building FastAPI or Flask endpoints to expose agent workflows to the frontend.Engineering PracticesContainerization: Package AI applications and models in Docker containers with proper dependency management and optimization for production workloadsCI/CD Pipeline Management: Build and maintain automated pipelines for testing, building, and deploying GenAI applications using Azure DevOps, GitHub Actions, or similarKubernetes Orchestration: Deploy and manage containerized AI services on Kubernetes, handling autoscaling, resource allocation, and service mesh configurationInfrastructure as Code: Define and version control infrastructure configurations, deployment manifests, and cloud resourcesVersion Control: Maintain clean Git workflows with proper branching strategies, meaningful commits, and thorough code reviewsMonitoring & Observability: Implement logging, tracing, and metrics collection for production AI systems; set up alerts and dashboards