SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Doctolib is seeking a Senior AI Engineer to join the Patient team in Paris, working on search and recommendation systems that serve 100M patients across Europe. You will design and build production search and recommendation engines that help patients navigate to the exact care they need while delivering trusted, curated health insights.
Key Responsibilities:
- Design and build production search and recommendation architecture, including full retrieval, ranking, and reranking pipelines using standard and off-the-shelf components (vector search, semantic retrieval, LLM/managed rerankers).
- Establish strong baselines first (prompts, RAG, model selection) before reaching for custom ML.
- Build evaluation and observability into every stage with offline and online evaluation frameworks.
- Set up data and event feedback loops that drive iteration and feed deeper ML work.
- Improve search relevance and ranking on patient-facing products to raise result quality.
- Own production quality: latency, reliability, monitoring, and maintainability.
- Partner with ML Engineers and collaborate closely with Product Managers and Software Engineers to define, build, and ship AI-powered features that deliver measurable value.
Doctolib's tech environment includes a cloud-native platform supporting web and mobile interfaces across multiple languages and healthcare specialties. The stack includes Rails, TypeScript, Java, Python, Kotlin, Swift, and React Native. The company invests in open, applied AI research, including the DoctoBERT project for open-source medical language models trained on French clinical text.
Position Details:
- Permanent, full-time role
- Location: Levallois, Paris
- Start date: As soon as possible
Requirements:
- Production deployment experience: ability to ship algorithms to production (ECS-based services on AWS).
- Strong analytical mindset with result-oriented, patient-first approach.
- Significant experience as a Software and/or AI Engineer shipping search or recommendation systems to production.
- Hands-on experience building end-to-end retrieval, ranking, and reranking pipelines; familiarity with nDCG, MAP, Recall@k, MRR metrics.
- AI-engineering proficiency: turning foundation models and off-the-shelf components into production systems (embeddings, vector search, semantic retrieval, RAG, LLM-based or managed rerankers like Vertex AI). Success does not require training models from scratch.
- Architecture-first approach: build systems, baselines, evals, and feedback loops with standard tooling before reaching for custom ML; know when to partner with ML Engineers.
- Evaluation and observability built into every stage (retrieval, ranker, reranker) with offline and online evaluation, A/B testing, position-bias handling, and monitoring.
- Production deployment capability: ship reliable, low-latency services (hundreds-of-ms SLAs) with care for data quality and long-term maintainability.
Nice-to-Have:
- Experience at B2C marketplaces (e-commerce, hospitality, travel).
- Additional ML methodologies: pattern mining, recommendation systems, experimentation, or causal inference.
- Search engine or information retrieval concepts experience.
- Exposure to learning-to-rank or feature engineering.
- Healthcare or regulated domain experience (GDPR, HDS compliance).
