We are looking for a Machine Learning Engineer specialized in Large Language Models (LLMs) and chatbot solutions.
The role focuses on designing, developing, and industrializing production-ready LLM solutions, including Retrieval-Augmented Generation (RAG) pipelines deployed on AWS infrastructure.
Main Responsibilities
-
Design and implement LLM-based chatbots for large structured and unstructured document collections.
-
Build and maintain RAG pipelines for retrieval and question answering.
-
Integrate ML models into AI-driven applications.
-
Develop serverless components using AWS Lambda, API Gateway, and event-driven services.
-
Work with vector search engines and indexing solutions.
-
Collaborate with ML, data, and product teams on scalable solutions.
Required Skills
-
Strong proficiency in Python.
-
Proven experience in Machine Learning Engineering.
-
Hands-on experience with LLM-based applications (chatbots, assistants, document AI).
-
Knowledge of RAG architectures and tools such as LangChain, LlamaIndex, or equivalent.
-
Experience with AWS services (Lambda, API Gateway, SQS, OpenSearch, etc.).
-
Fluent Italian and good English skills.
Job Details
-
Employment type: Full-time
-
Work model: Remote