JR/MID AI ENGINEER

Questa posizione è in Kirey

Il processo di selezione sarà interamente gestito Kirey.

Questa opportunità è disponibile in Roma - Italy, Milano - Italy, Firenze - Italy.

--

YOUR NEW COMPANY Kirey is one of the leading European groups specializing in technology consulting and system integration, with a distinctive positioning in data-driven innovation. Through a comprehensive portfolio of solutions—including Data & AI, Cloud, Software Development, Cybersecurity, Infrastructure & Automation, and Monitoring—Kirey transforms data complexity into intuitive and accessible solutions, enabling its clients to achieve their business objectives. Headquartered in Italy, with a solid international presence and nearly 1,500 employees, Kirey has delivered more than 10,000 projects for leading clients across industries such as Insurance, Banking, Manufacturing, Retail, Public Administration, and Services & Energy. At the core of all this are people, who at Kirey are empowered to fully express their talent and actively contribute to the company’s value chain. This is made possible through continuous investment in improvement processes and training, the promotion of innovative ideas and creativity through skills development, and a strong commitment—expressed through dedicated initiatives—to inclusion and diversity. Kirey Group's AI & Innovation Business Unit designs and delivers AI-driven solutions for leading companies across industries such as pharma, manufacturing and financial services. We help our clients turn data into value through Generative AI, advanced analytics and modern data platforms like AWS, Databricks, Microsoft Fabric and Azure. YOUR ROLE Join our AI & Innovation Business Unit as a Jr/Mid AI Engineer. You will work on real client projects involving Generative AI, agentic solutions and data platforms — building intelligent agents on AWS Bedrock and/or Databricks Genie, while designing and implementing the data pipelines that power them. Locations: Milan, Florence, Rome — hybrid working model. We are looking for a motivated AI Engineer with 1 to 3 years of experience to join our team. You will work hands-on with senior engineers on client projects, combining agentic AI development — using AWS Bedrock Agents and/or Databricks Genie — with solid data engineering fundamentals, from data modeling to the design and implementation of ingestion pipelines. You will contribute to projects such as AI agents, Retrieval-Augmented Generation (RAG) systems, automated data analysis and interactive dashboards, working in a collaborative, innovation-oriented environment

Responsibilities

.Design and develop Generative AI solutions, including LLM-based agents and RAG pipelines, using AWS Bedrock Agents and/or Databricks Genie.

• Design, write and iterate on prompts for LLM-based agents, optimizing for accuracy, reliability and cost across different models and use cases.
• Model data and build data pipelines, developing and maintaining ingestion processes on AWS and/or Databricks.
• Develop and maintain data models on platforms such as AWS , Databricks
• Write clean, well-documented Python code and contribute to testing and quality assurance of AI components.
• Help evaluate and monitor AI solutions, measuring accuracy, performance and reliability.
• Build dashboards and data visualizations to present insights to business users.
• Collaborate with senior engineers, consultants and client teams throughout the project lifecycle.
• Stay up to date with the latest developments in AI and share new ideas with the team.

Requirements

• Bachelor's or Master's degree in Computer Science, Computer Engineering, Data Science, Mathematics, Physics or a related field.
• 1 to 3 years of experience in AI/data engineering roles.
• Hands-on experience with AWS Bedrock Agents and/or Databricks Genie for building agentic AI solutions.
• Practical experience in prompt engineering, including prompt design, iterative refinement and evaluation techniques for LLM-based applications.
• Proven experience in data modeling and building data ingestion pipelines on AWS (e.g. Glue, Lambda, S3) and/or Databricks.
• Good programming skills in Python and SQL.
• Solid understanding of machine learning concepts and familiarity with Large Language Models.
• Good knowledge of cloud platforms (AWS and/or DataBricks) and modern data tools.
• Curiosity, willingness to learn and a proactive attitude.
• Good communication skills and the ability to work in a team.
• Good knowledge of English, both written and spoken; Italian is required.

Nice to have: experience with frameworks such as LangChain or LangGraph, AWS or