AI Full-Stack Engineer
Pubblicato il 24-10-2026 - Dicto AI in Italia
We’re looking for a full-stack engineer with strong NodeJS / Python experience, combined with solid MERN-stack development skills. This role mixes applied AI work, backend engineering, and full product delivery. You’ll work across data pipelines, APIs, model integration, retrieval-augmented generation (RAG) systems, and cloud-native deployments. Responsibilities Build and maintain full-stack applications using the MERN stack (NestJS, React, TypeScript). Develop backend services and AI-driven features using TypeScript. Help to maintain RAG pipelines, vector databases, embeddings workflows, and model-serving integrations. Implement scalable APIs and microservices integrating ML or LLM-based components. Deploy and manage services in AWS and/or GCP (compute, storage, networking, CI/CD). Work with PostgreSQL, Redis and Qdrant for structured and unstructured data. Collaborate with product and technical teams to take AI-powered features from prototype to production. Maintain quality, performance, and reliability across the stack. Required Skills Strong TypeScript experience for backend development and applied ML. Hands-on experience building RAG systems:
vector stores, retrieval layers, embedding models. Solid understanding of LLM integration, prompt patterns, and model-serving frameworks. MERN-stack experience with strong React proficiency. Strong Node.js and Express experience for API development. Proficiency with PostgreSQL and database-schema design. Experience deploying both traditional and ML workloads on AWS or GCP. Good grasp of distributed systems, containers, and CI/CD workflows. Nice to Have Work across ML workflows: data ingestion, preprocessing, inference, and evaluation. Experience with Haystack, or similar frameworks. Exposure to GPU workflows, inference optimization, or fine-tuning. Familiarity with serverless environments. Experience with observability tools across backend and ML systems. Profile Comfortable owning work across backend, frontend, and ML integration. Able to move quickly between prototyping and production-grade implementation. Pragmatic, product-oriented, and comfortable operating in ambiguous environments.