Senior AI Engineer – Agentic Systems
Pubblicato il 16-09-2026 - Jobgether in Italia
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior AI Engineer – Agentic Systems & LLM Applications based in Italy.
This role sits at the intersection of product engineering and frontier AI, focused on building the next generation of AI-native applications.
You will design and scale autonomous agents capable of reasoning, taking actions, and solving complex, non-deterministic workflows in production.
The position combines LLM application development, agent orchestration, advanced retrieval, developer tooling, and production AI engineering.
You will work with leading foundation models and modern AI infrastructure to create reliable, observable, and low-latency systems.
A major focus will be moving AI solutions beyond prototypes by implementing rigorous evaluation, monitoring, and optimization practices.
As part of a distributed, global-first team, you will have significant ownership over technical architecture and product direction.
This is an opportunity to work on challenging AI problems while turning emerging capabilities into practical products with tangible user impact.
Accountabilities:
- Design and implement autonomous agents and multi-agent orchestration systems capable of handling complex, open-ended tasks.
- Build and optimize production-grade applications on top of leading foundation models, with a focus on reliability, observability, scalability, and low-latency performance.
- Architect advanced Retrieval-Augmented Generation (RAG) pipelines and vector database strategies that provide agents with accurate, relevant, and real-time context.
- Develop sophisticated tool-calling, planning, reasoning, and autonomous execution workflows for AI agents.
- Contribute to AI-powered developer tools and internal frameworks that accelerate the development and deployment of AI-native products.
- Establish rigorous evaluation frameworks and Evals to measure model and agent performanc