Tech Lead Data Retrieval / RAG - Python & Search - Freelance (H/F)

France | Oct. 29, 2026

Report as Closed

Company: Collective.work

Country: France

Type: Hybrid remote

Employment: Full-time

Description: Want to take on a new challenge around Data and AI? CELAD is waiting for you! Are you passionate about information retrieval, data architectures and generative AI? Do you want to work on large-scale volumetrics, indexing and relevance issues? We are looking for a Data Retrieval / RAG Tech Lead to join a player in the legal publishing and Legaltech sector, based in La Défense. As part of a team specializing in AI services, you will contribute to the design of the data base which powers intelligent applications intended for legal professionals. YOUR ROLE You will be the technical referent on the collection, ingestion, transformation and indexing of large documentary corpora. Your goal: to design reliable and scalable pipelines, while optimizing the relevance of results from hybrid search engines and RAG systems. YOUR MAIN MISSIONS *    Data ingestion: design pipelines capable of collecting and processing heterogeneous sources, ensuring parsing, cleaning, chunking and normalization of documents. *    Indexing: industrialize indexing and embedding mechanisms on large corpora, guaranteeing the freshness and consistency of indexes. *    Information search: design search strategies combining lexical search, semantic search, BM25, embeddings and reranking. *    Optimization of relevance: define metrics and test sets to measure and improve the quality of the retrieval. *    RAG architecture: structure the recovery of documents and context transmitted to LLMs, by managing citations, deduplication and context windows. *    Quality and traceability: set up versioning of datasets and indexes, data lineage and supervision mechanisms. *    Security: contribute to the protection of data, the compartmentalization of processing and compliance with regulatory requirements. *    Technical leadership: support teams, promote good development practices and contribute to architecture choices. TECHNICAL ENVIRONMENT *    Languages: Python 3.11+, Go appreciated. *    Search and indexing: OpenSearch, Elasticsearch, pgvector, Weaviate, Qdrant, BM25, hybrid search. *    AI and NLP: embeddings, sentence-transformers, tokenization, document parsing, reranking, RAG, LangChain. *   LLM: OpenAI, Mistral, Bedrock or equivalent technologies. *    Data engineering: PostgreSQL, Airflow, Spark or equivalent. *    Infrastructure: Kafka, Redis, Docker, CI/CD, Kubernetes. *    Tests and evaluation: Pytest, precision, recall, nDCG, MRR. *    You have at least 9 years of professional experience excluding internships and work-study programs, with expertise in data engineering, search engines or retrieval information. *    You have designed and operated data pipelines in production on large volumes. *    You master indexing mechanisms, embeddings and hybrid search approaches. *    You know how to objectively evaluate the relevance of a search engine and implement improvement actions. *    You understand RAG architectures and the role of retrieval in the quality of answers generated by LLMs. *    You are able to take a step back from technical choices, define standards and support other developers. *    You have fluent professional English to operate in an international context. Higher education in computer science, data or artificial intelligence (Master's degree, doctorate or equivalent) is expected. WHY JOIN THIS PROJECT? *    Participate in building a large-scale intelligent search engine. * Contribute

Apply here:

Web: Apply here

Emails: