Generative AI Full-Stack Engineer

Azienda Anonima

Udine

In loco

EUR 60.000 - 90.000

Tempo pieno

6 giorni fa

Candidati tra i primi

Generatore di candidature

Ottieni una risposta da questo datore di lavoro — un curriculum e una lettera di presentazione personalizzati, che corrispondono esattamente a ciò che sta cercando.

Supera i filtri ATS

Descrizione del lavoro

Azienda Anonima is seeking an experienced AI Engineer – Full Stack to design and develop next-generation AI-powered products in a fast-paced startup environment in Udine, Italy. You will build end-to-end Generative AI systems, from data ingestion and knowledge retrieval to production deployment, collaborating with frontend engineers to deliver AI-powered user experiences.

Ideal candidates have strong software engineering fundamentals, hands-on experience with LLMs, RAG/Graph RAG, and

Competenze

5+ years of experience in Software Engineering with exposure to Generative AI tech.
Proficient in Python (FastAPI) and/or Node.js (Express/NestJS).
Hands-on with LLMs, prompt engineering, AI orchestration frameworks, and AI Agents.
Solid understanding of RAG, embeddings, vector DBs, and knowledge management architectures.
Experience with PostgreSQL, MongoDB, and vector databases.
Frontend familiarity with React or Vue.js, TypeScript, and modern web practices.
Experience with Docker, Kubernetes, CI/CD, and AWS/GCP.
Familiarity with REST APIs, GraphQL, authentication, and scalable distributed systems.
Strong software engineering fundamentals, code quality, testing, and documentation.

Mansioni

Design and maintain LLM-based Generative AI pipelines with low latency.
Build Retrieval-Augmented Generation (RAG) solutions and embeddings workflows.
Develop Graph RAG architectures using knowledge graphs for reasoning and traceability.
Create AI Agents and orchestrated workflows with function calling and multi-step reasoning.
Evaluate multiple LLMs (OpenAI, Anthropic, Gemini, Llama, Mistral) for performance and cost.
Design scalable REST APIs and backend services for AI capabilities.
Work with vector and graph databases to support knowledge management and retrieval.
Collaborate with frontend engineers for AI-powered conversational interfaces.
Optimize AI apps for scalability, reliability, and cloud cost efficiency.
Implement security best practices and prompt-injection mitigations.
Monitor AI systems using evaluation metrics and latency targets.