Generative AI Engineer — Full-Stack Innovator

Azienda Anonima; Mantova; In loco; EUR 70.000 - 110.000; Tempo pieno

Descrizione del lavoro

Azienda Anonima in Lombardy seeks an experienced AI Engineer – Full Stack to design and deploy end-to-end AI-powered products. You will drive data ingestion, retrieval, and production deployment in a fast-paced startup environment.

Responsibilities include building LLM-based pipelines, RAG architectures with embeddings and vector databases, and scalable REST APIs. Collaboration with frontend teams and cloud-native optimization are key aspects of the role.

Competenze

• 5+ years of experience in Software Engineering with Generative AI exposure.
• Proficiency in Python (FastAPI) and/or Node.js (Express or NestJS).
• Hands-on with LLMs, prompt engineering, and AI orchestration frameworks (LangChain, LangGraph, LlamaIndex).
• Solid understanding of RAG, embeddings, semantic search, vector databases, and knowledge management.
• Experience with PostgreSQL, MongoDB, and vector databases.
• Frontend familiarity (React or Vue.js), TypeScript, and modern web practices.
• Experience with Docker, Kubernetes, CI/CD, and AWS/GCP.
• Knowledge of REST, GraphQL, authentication, and scalable architecture.
• Strong coding, testing, documentation, and code review habits.
• Ability to work in cross-functional international teams.

Mansioni

• Design, develop, and maintain LLM-based Generative AI pipelines with high quality and low latency.
• Build Retrieval-Augmented Generation (RAG) solutions with embedding and vector search.
• Design Graph RAG architectures using knowledge graphs for reasoning and traceability.
• Develop AI Agents and orchestrated workflows with function calling and multi-step reasoning.
• Integrate leading LLMs (OpenAI, Anthropic, Gemini, Llama, Mistral) and evaluate trade-offs.
• Create scalable REST APIs and backend services for AI capabilities.
• Collaborate with frontend engineers for AI-powered UIs and experiences.
• Optimize AI apps for scalability, reliability, and cost in cloud native environments.
• Implement security, authentication, and prompt-injection mitigation.
• Monitor AI systems using evaluation metrics and latency/quality targets.

Conoscenze

Python (FastAPI)

Node.js (Express or NestJS)

LLMs / Prompt engineering

RAG / embeddings

REST APIs / GraphQL

Docker / Kubernetes

Cloud platforms (AWS/GCP)

Strumenti

LangChain

LangGraph

LlamaIndex

Pinecone

Weaviate

Milvus

pgvector

Neo4j

Descrizione del lavoro

Azienda Anonima in Lombardy seeks an experienced AI Engineer – Full Stack to design and deploy end-to-end AI-powered products. You will drive data ingestion, retrieval, and production deployment in a fast-paced startup environment.

Responsibilities include building LLM-based pipelines, RAG architectures with embeddings and vector databases, and scalable REST APIs. Collaboration with frontend teams and cloud-native optimization are key aspects of the role.