Senior AI Engineer - Search & Recommendation - Patient Team (x/f/m)

Doctolib

Paris, Île-de-France

Join our mission, join Doctolib! We are looking for a Senior AI Engineer to join the Patient team in Paris. The Patient domain sits at the heart of Doctolib's mission: ensuring everyone has better access to the care they need, receives better care from health professionals, and can actively prevent health problems to improve their wellbeing. You’ll design the search and recommendation engines behind our health companion, helping 100M patients across Europe instantly navigate to the exact care they need while delivering trusted, curated insights at every step. The retrieval and recommendation architecture you own will directly shape how relevant, fast, and trustworthy that experience is for every one of them. Your responsibilities include but are not limited to: Design and build the production search & recommendation architecture: full retrieval, ranking, reranking pipeline with 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. Set up the data/event feed

Requisitos

Design and build the production search & recommendation architecture: full retrieval, ranking, reranking pipeline with 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. Set up the data/event feedback loops that drive iteration and feed deeper ML later. Improve search relevance and ranking on Patient facing products , raising result quality Own production quality: latency reliability, monitoring, and maintainability. Partner with ML Engineers and collaborate closely with PMs and…

Ref. W7JOD

Info
-- / --
Info

Arrastra un PDF aquí, pega una URL o toca para seleccionar un archivo