Senior AI Engineer

16 ore fa

Ro, Emilia-Romagna, Italia NTT DATA Europe & Latam Tempo pieno
Who We Are We operate beyond organizational silos, combining deep expertise in data engineering and AI-driven solutions to design and deliver scalable, user-centric applications and modern data architectures. We support a wide range of industries, including Automotive, Banking, Insurance, Telecommunications, E-commerce, and Public Services. Our focus is on building robust, enterprise-grade data platforms and enabling advanced analytics and AI capabilities within the Microsoft ecosystem, including Azure, Microsoft Fabric, and the Power Platform. We specialize in designing secure, high-performance solutions that integrate data pipelines, AI models, and Generative AI use cases to deliver real business value. What You'll Be Doing
• Design and implement enterprise RAG solutions for engineering, technical-case, supplier, and licensing content, covering chunking, metadata, permissions, hybrid retrieval, reranking, grounding, and citations.
• Develop controlled document-generation solutions for proposals, reports, and regulated documents using templates, citations, and version control.
• Build multi-step AI agents covering planning, state, memory, tool calling, routing, structured outputs, retries, and failure recovery.
• Integrate agents with enterprise systems such as PLM, ERP, CPQ, and case management platforms, including controlled write-back through human approval.
• Implement interactions with structured data using text-to-SQL and connect forecasting, optimization, and document-extraction models as reusable agent tools.
• Evaluate retrieval quality, groundedness, task success, and tool correctness within a shared evaluation framework, including detailed failure analysis of agent runs.
• Implement guardrails, tracing, auditability, monitoring, and observability for LLM and agent actions.
• Collaborate with AI Architects, domain experts, and platform engineers to define technical baselines and measurable business outcomes, including engineering hours removed, First Pass Yield, and lead-time improvements.
• Deliver reusable and tested Python code, version-controlled prompts, models, configurations, and supporting technical documentation.
• Support iterative MVP releases, incorporate user feedback, and ensure effective production handover and monitoring. What You'll Bring Along
• At least 10 years of relevant technology experience
• At least 6 years of experience in data science, machine learning, or natural language processing, including hands-on production work with LLMs.
• At least 4 years of strong hands-on experience with Python and SQL.
• Proven experience delivering production-grade RAG, LLM, or agentic AI solutions.
• Strong knowledge of enterprise RAG, embeddings, vector and hybrid search, reranking, grounding, citations, prompt design, structured generation, tool calling, and agent orchestration.
• Strong understanding of agent state, memory, routing, human approval patterns, failure recovery, evaluation, guardrails, tracing, and observability.
• Experience with cloud deployment, monitoring, and LLMOps practices.
• Strong technical communication, stakeholder influence, ownership, mentoring, and sound judgment in ambiguous environments.
• Knowledge of knowledge graphs, ontologies, process mining, workflow analysis, open-source models, model gateways, MCP, A2A protocols, or document intelligence is considered an advantage.
• Experience with Amazon Bedrock, including Agents, AgentCore, and Knowledge Bases, as well as LangChain, LangGraph, CrewAI, or comparable frameworks, is preferred.
• Experience with Amazon OpenSearch, PostgreSQL with pgvector, AWS S3, Lambda, API Gateway, EKS or ECS, and CloudWatch is considered an advantage.
• Experience working with engineering, energy, regulated, or export-controlled content, as well as consulting or client-facing delivery experience, is preferred.
• Excellent command of both spoken and written English.