Description du poste
<h2><strong>What you’ll do</strong></h2> <p>At Doctolib, we're on a mission to transform healthcare through the power of AI. As a <strong>Senior Data Engineer</strong>, you'll play a key role in building and optimizing the data foundations within the AI Team to deliver safe, scalable, and impactful models.</p> <p>You will join a dedicated team working on data infrastructure for <strong>LLM, VLM and RAG-based systems</strong>, powering our new <strong>AI Medical Companion</strong>.</p> <p>Your work will ensure that our engineers and data scientists can <strong>train, evaluate, and deploy AI models</strong> efficiently on high-quality, well-structured, and compliant data.</p> <p>Your responsibilities include but are not limited to:</p> <ul> <li><strong>Ensure high standards of data quality for AI model inputs.</strong></li> <li><strong>Design, build, and maintain scalable data pipelines</strong> on <strong>Google Cloud Platform (GCP)</strong> for AI and machine learning use cases.</li> <li><strong>Implement data ingestion and transformation frameworks</strong> that power <strong>Retrieval</strong> systems and <strong>training datasets</strong> for LLMs and multimodal models.</li> <li><strong>Architect and manage NoSQL and Vector Databases</strong> to store and retrieve embeddings, documents, and model inputs efficiently.</li> <li><strong>Collaborate with ML and platform teams</strong> to define data schemas, partitioning strategies, and governance rules that ensure privacy, scalability, and reliability.</li> <li><strong>Integrate unstructured and structured data sources</strong> (text, speech,image, documents, metadata) into unified data models ready for AI consumpt