Data Engineer (NLP & Unstructured Data)
Role details
Job location
Tech stack
Job description
For an important mission with a major Life Sciences client, you will join a project team working on generative AI solutions to answer concrete business needs: automation, smart search, and value creation from unstructured data (documents, scans, emails, multimedia).
Your role will be key in designing and deploying strong data pipelines to ingest, process, enrich and serve different types of content for NLP, RAG and analytics use cases.
You will join our Data & AI practice and work with technical and business experts to build innovative tools that improve automatic writing, information search and advanced analysis, while ensuring security and data compliance.
Requirements
- University degree or engineering school in computer science, mathematics, data science or similar.
- At least 5 years of experience in similar environments.
- Strong knowledge of Python and SQL; experience with document pipelines and OCR.
- NLP experience for unstructured data (NER, summarization, semantic search).
- Experience building RAG solutions., * Knowledge of knowledge graphs and query languages (SPARQL, Cypher).
- Familiarity with translation/grounding use cases using OpenSearch Memories.
- Experience in regulated environments (e.g., Life Sciences).