h3Overview /h3pAs part of the msg group, you will translate business processes into reliable, production-ready AI agents and systems. You design end-to-end pipelines, selection of tools, and human handoffs to ensure accuracy and trust in deployed models. You focus on turning complex domain logic into testable, measurable solutions with clear ownership of quality. This role combines engineering rigor with business impact, delivering scalable retrieval, grounding, and evaluation capabilities. A meaningful chance to shape how AI touches real work for leading enterprises. /ph3Retribuzione / Benefits /h3ullicompetitive salaries 55.000 - 65.000 Eur /lilibroad range of benefits /lilidiversity and cultural differences are cherished /li /ulh3Responsabilità /h3ulliDecompose business processes into steps, tools, handoffs, and decision points for agent-based execution /liliDesign and implement retrieval pipelines with chunking, embedding models, hybrid search, and grounding to source data /liliTreat prompt and context engineering as an engineering discipline with versioning, tests, and measurement /liliBuild the evaluation layer with datasets, automated scoring, and regression suites /liliInstrument production systems for observability: traces, latency, costs, failure rates, and drift /liliOwn end-to-end quality and diagnose failures to their root cause across retrieval, reasoning, tooling, or data /liliBalance model quality, cost, and latency,



adapting choices as models evolve /liliCollaborate with business experts to extract domain logic and translate it into testable artifacts /liliTake agents into production with platform and infrastructure teams and monitor live behavior /li /ulh3Requisiti fondamentali /h3ulli5+ years software development experience, 2+ years with production LLM-based systems /liliStrong Python fundamentals: version control, tests, code reviews, incremental delivery /liliExperience with async work, FastAPI and Pydantic or equivalents /liliHands-on with at least one agent orchestration framework (LangGraph, LlamaIndex Workflows, OpenAI Agents SDK, Temporal) /liliExperience serving models via managed platforms (AWS Bedrock, Azure AI Foundry, Google Vertex AI) or provider APIs with streaming, structured output, prompt caching, rate-limiting /liliProduction vector search experience (pgvector, Qdrant, Pinecone, Weaviate, Milvus, Azure AI Search) with understanding of trade-offs /liliDeep retrieval expertise (chunking, metadata filtering, query rewriting, hybrid search, reranking) /liliFluent in tool and function calling, structured output, and multi-step agent design /liliHands-on with Model Context Protocol (MCP): building servers, tool interfaces, auth and error handling /liliEvidence of a solid evaluation discipline and a measurable eval harness /liliAbility to work with business experts to produce workable specifications /liliJudgment to select appropriate tools vs rules engines and plain queries /liliFluent English /li /ulullicomfort with ambiguity /lilistrong communication with business stakeholders /lilicollaboration across cross-functional teams /liliPython /liliFastAPI /liliPydantic /li /ul #J-18808-Ljbffr

📌 Senior AI Engineer (Monza)
🏢 msg group
📍 Monza