Python AI Developer (M/F)

France | Nov. 12, 2026

Report as Closed

Company: RGI S.p.A.

Country: France

Type: Hybrid remote

Employment: Full-time

Description: Python AI Developer (M/F)Paris/Lille / Insurance SectorWhy this opportunity?Because you will participate in the construction of our artificial intelligence strategy, which we are in the process of defining.You will join a motivated and talented team, whose mission is to integrate AI into the heart of our business processes.The objective is to meet the needs of our teams as well as those of our clients, and to automate certain tasks with low added value.Key elements* Design solutions RAG and agentics applied to concrete business use cases.* Develop and orchestrate agents while ensuring source traceability and control of hallucinations.* Contribute directly to the KELIA product configuration workflow, with human validation integrated into key stages.* Participate in the production of assistants, from their API to their integration into the internal web interface. What you need to know: We are looking for a Python AI Developer to join our R\&D team in Paris or Lille You will be involved in the entire life cycle of the solutions, from design to production, using different approaches: language models (LLM), supervised learning, clustering and other machine learning techniques. An important part of the mission also concerns product configuration: the objective is to extract relevant information from the general conditions, to propose a configuration, to provide validation by an expert at each stage and to produce a file that can be directly imported into KELIA.Main missions: You develop AI functionalities in Python.* Document ingestion: extract text and tables from PDFs, Confluence pages, SharePoint documents and GitLab repositories, then slice, index and update this content with asynchronous jobs.* Search: hybrid search (semantic and keywords), filters by collection and by path, reranking, and visual search on document pages.* Agents and LLM: develop agents with LangGraph (routing, search, filtering, reflection, response), write and version prompts, cite sources, and respond “I can't find” when information is missing.* Product configuration workflow: contribute to the agent who extracts information from the general conditions, proposes the configuration, has each step validated by an expert and produces a file that can be imported into KELIA.* Quality: maintain test sets, measure the rate of correct answers, track invented responses and check that the results are stable from one run to the next. the other.* Cost and latency: track token consumption, first response time and cache, and choose the right model for each task.* API: expose wizards in API, with streaming responses, and integrate them into the internal web interface.* Document your code, write tests and participate in code reviews. This position is for you if:* You have a Bachelor's degree in IT or insurance* You are proficient in Python 3.11+ and are comfortable with API development via FastAPI, Pydantic and SSE streaming.* You have experience or a real interest in generative AI solutions, LLMs and agentic architectures with LangChain, LangGraph and LiteLLM.* You know the principles of RAG, hybrid search, embeddings and reranking, ideally with Qdrant.* You know how to work with various documentary sources and their ingestion, notably PDFs, Confluence, SharePoint or GitLab, with tools such as Docling.* You are comfortable with storage and persistence environments based on PostgreSQL and S3 object storage.* You attach importance to the observability and quality of AI solutions, in particular the monitoring of prompts, traces, logs, costs and performance, with tools such as MLflow.* You are aware of security, authentication and data management issues. roles, particularly with Keycloak.* You evolve with ease in a modern industrialization environment using Git, GitLab CI, Docker, Kubernetes, Helm and pytest, as well as collaborative tools like Jira and Confluence. What you bring* A good command of Python and its best practices: testing (pytest), typing, dependency management.* Your experience in using LLM APIs and the basics of prompt engineering, including outputs structured.* Your understanding of how a RAG works: embeddings, division, search, generation.* A good command of SQL and database concepts.* Git and teamwork.Why join us:* To contribute to a strategy where artificial intelligence is a key lever of the technological roadmap, with solutions integrated into the heart of business tools.* To work on cases of...

Apply here:

Web: Apply here

Emails: